Trends in our coverage

A count of what CYBERNOISE has covered, not a measure of research activity across science.

Coverage as of 2026-11-05 UTC

The current seven-day window is 2026-10-30–2026-11-05 inclusive; the preceding seven-day window is 2026-10-23–2026-10-29 inclusive. Dates are source publication dates converted to UTC, not article publication, retrieval or index dates.

The full index contains 558 source records across all topics and dates. 2 have unknown or invalid source dates and 0 have source dates after the as-of date; neither is included in the windows. Older records remain in full-corpus counts.

Counts cover the entire indexed corpus, not search results or a retrieved sample. Each indexed article/source record counts once per topic and once per normalized keyword. Separate versions of the same paper can appear as separate records and may inflate counts. Metadata keywords are article labels, not AI-inferred themes or a standardized scientific vocabulary: case and whitespace are normalized, but synonyms are not merged. These counts reflect editorial selection and metadata, not prevalence in the wider literature.

Topic coverage

Indexed records by topic and source publication date
Topic	Full corpus	Current seven days	Previous seven days	Change
Artificial Intelligence	345	304	20	+284
Plant Biology	56	46	8	+38
Economics	157	111	17	+94
Astrophysics	0	0	0	0

Only keywords attached to at least 3 distinct current-window records are shown below. A missing keyword is not evidence of absence from the literature or even from our coverage.

Artificial Intelligence keywords

large language models Current 56 Previous 2 Change +54

Current window · 56 articles

PatchScout tackles web research by deciding when to move on 2026-10-30 UTC
AI Can Write SQL. Making It Trustworthy Takes More Than a Bigger Model 2026-10-30 UTC
Taurus targets cheaper CT labeling by giving AI fewer, clearer decisions 2026-10-30 UTC
When AI Gets the Score Right but the Work Wrong 2026-10-30 UTC
Medical AI scores fall sharply when answer choices disappear 2026-10-30 UTC
TAILOR targets the risky tail of AI-generated computer-system heuristics 2026-10-31 UTC
When AI Conversations Go Off Track, Rebuilding Context Can Help 2026-10-31 UTC
Exact Replay Does Not Guarantee Stable AI Deliberation 2026-10-31 UTC
WAR-CRAFT audits API recommendations against application requirements 2026-10-31 UTC
Physicians preferred conversational database queries, but accuracy remained a concern 2026-10-31 UTC
TopoQuant probes how compression changes language models’ attention 2026-10-31 UTC
Evidence-trained AI helps design a better contact for perovskite solar cells 2026-10-31 UTC
Can a Small Selector Learn Which Examples Help a Language Model? 2026-10-31 UTC
A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
A Formula-Aware Map Helps AI Navigate Spreadsheets with Less Data 2026-10-30 UTC
A layer-by-layer merging method aims to shorten AI reasoning without retraining 2026-11-02 UTC
Scripted automation beats an AI agent on a stable laboratory portal 2026-11-02 UTC
AI models produce different opinion dynamics under the same discussion rules 2026-11-02 UTC
When community beliefs steer AI toward cooperation—or free-riding 2026-11-02 UTC
Choosing Less-Repetitive Training Data Could Make AI Fine-Tuning More Efficient 2026-11-02 UTC
AlgoPilot teaches language models to choose a solving strategy before answering 2026-11-02 UTC
How Worse Model Variants Can Still Guide Better AI Training 2026-11-03 UTC
A two-stage reasoning system helps AI choose Earth-observation evidence 2026-11-03 UTC
One AI can plan the program while another writes the code 2026-11-03 UTC
Keeping AI agents within their assigned authority 2026-11-03 UTC
FP4Quant speeds up GPU communication, with a measurable accuracy trade-off 2026-11-03 UTC
When 4-Bit AI Models Run Faster—and When the Advantage Disappears 2026-11-03 UTC
Stricter AI checks did not consistently improve research results in two tests 2026-11-03 UTC
Language Models Help Tune the Search for Better Satellite Imaging Schedules 2026-11-03 UTC
Specialist AI assistants do not always give better regulatory answers 2026-11-03 UTC
When One Steering Direction Is Not Enough for a Language Model 2026-11-03 UTC
TactiNavi Gives an AI Game Coach Rules for When Advice Applies 2026-11-03 UTC
When AI Agents Agree, Their Majority Can Still Be Wrong 2026-11-03 UTC
When AI learns new facts, its confidence may lag behind 2026-11-03 UTC
ALBI pairs AI-generated logic rules with a Prolog checker 2026-11-03 UTC
The Same Citizens’ Views Can Yield Different AI Policy Proposals 2026-11-03 UTC
Can an AI Model Forget—or Just Stop Answering? 2026-11-03 UTC
LLM game characters: a research map reveals gaps in speed, safety and memory 2026-11-02 UTC
LIBRA tests tool connections to help AI agents find missing prerequisites 2026-11-03 UTC
Bloomberg’s AI-assisted code migrations hit a human review bottleneck 2026-11-03 UTC
AI literature reviews: better access helps, but expert judgment still matters 2026-11-03 UTC
Choosing Which AI Preferences to Label—and When Disagreement Helps 2026-11-03 UTC
CoCo turns textual context into numerical guidance for time-series forecasts 2026-11-03 UTC
Teaching AI when to ask another question—and when to stop 2026-11-03 UTC
Hybrid Spark pairs prediction with copying to speed up AI code editing 2026-11-03 UTC
AI judges can check the evidence and still follow a false expert cue 2026-11-03 UTC
TACT puts an AI council to work on qualitative data—with humans retaining judgment 2026-11-03 UTC
Expert Feedback Helps AI Refine Finance Briefs—but Strong Answers Can Get Worse 2026-11-03 UTC
AI forecasts of freelance-job success improve when models know the agent’s limits 2026-11-03 UTC
AI author imitation can look convincing to a metric by copying the examples 2026-11-04 UTC
Who Gets to Shape AI? The Case for Distributed Alignment 2026-11-04 UTC
Making AI Forget—and Giving Providers Something to Audit 2026-11-04 UTC
When graphs help AI agents—and why better retrieval is not enough 2026-11-04 UTC
Teaching smart homes to untangle who triggered each sensor 2026-11-04 UTC
MA-Mesh Gives AI Agent Teams a Way to Review and Replace Failing Peers 2026-11-04 UTC
Temporarily disabling safety neurons could make AI models harder to jailbreak 2026-11-04 UTC

Previous window · 2 articles

Study compares human and AI-simulated clients in counselling role-plays 2026-10-29 UTC
TextSeal2 aims to preserve AI text watermarks during faster decoding 2026-10-29 UTC

ai agents Current 46 Previous 3 Change +43

Current window · 46 articles

MemU-Bench tests whether AI phone assistants can remember what users leave unsaid 2026-10-30 UTC
Taurus targets cheaper CT labeling by giving AI fewer, clearer decisions 2026-10-30 UTC
AI Safeguards Need to Be Judged by How They Fail Together 2026-10-30 UTC
When AI Gets the Score Right but the Work Wrong 2026-10-30 UTC
Exo lets AI agents rewrite their harness while working 2026-10-30 UTC
Skill++: Helping AI agents find the right skills as their libraries grow 2026-10-31 UTC
Catching Silent Errors in the Compiler Behind TPU Workloads 2026-10-31 UTC
MemSidecar puts AI memory retrieval on a separate track 2026-10-31 UTC
Could sleep-inspired maintenance help AI agents manage their memories? 2026-11-01 UTC
Fármaco AI agent coordinates drug-discovery tools through a shared scientific database 2026-11-02 UTC
Scripted automation beats an AI agent on a stable laboratory portal 2026-11-02 UTC
AI models produce different opinion dynamics under the same discussion rules 2026-11-02 UTC
WASP-Mem preprint tests wiki-style memory for workplace AI agents 2026-11-02 UTC
Recursa improves AI legal research by revising its own working knowledge 2026-11-02 UTC
A shared task board for AI agents that need to wait 2026-11-03 UTC
GlucoAgent tests a case-by-case approach to glucose forecasting 2026-11-03 UTC
DualWorldBench tests whether AI agents can turn delivery goals into workable plans 2026-11-03 UTC
Harness-S trains AI agents to retain lessons from specialized execution support 2026-11-03 UTC
Preprint Finds Hidden Evaluation Errors Can Reshuffle AI Agent Rankings 2026-11-03 UTC
CogniLife proposes a way for AI experts to learn from their creators 2026-11-03 UTC
Signals: Diagnosing AI Agents Beyond Successful Tool Calls 2026-11-03 UTC
When AI Agents Agree, Their Majority Can Still Be Wrong 2026-11-03 UTC
Meta² teaches AI agents when to change their working setup 2026-11-03 UTC
AgentAM puts metal-printing models behind a conversational interface 2026-11-03 UTC
Can AI agents work with less context? A study tests compact memory and selective reading 2026-11-03 UTC
LIBRA tests tool connections to help AI agents find missing prerequisites 2026-11-03 UTC
AI agents remember useful lessons—but struggle to keep them current 2026-11-03 UTC
SlackBench tests whether AI agents can piece together a collaborative project 2026-11-03 UTC
VirtualTrialHarness reports gains in turning clinical protocols into executable cohorts 2026-11-03 UTC
Anduin proposes payment-based reputation for AI-agent marketplaces 2026-11-03 UTC
When AI agents change, should their permissions change too? 2026-11-03 UTC
Training AI Agents to Remember—and Check Their Memories 2026-11-03 UTC
Why AI failure explanations need a replay test, researchers argue 2026-11-03 UTC
Reading a Chart Accurately Did Not Guarantee Better AI Decisions 2026-11-03 UTC
AI agents may not need every reasoning trace their teachers produce 2026-11-03 UTC
AI forecasts of freelance-job success improve when models know the agent’s limits 2026-11-03 UTC
AI agents carry electricity-planning scenarios through design, testing and revision 2026-11-04 UTC
When graphs help AI agents—and why better retrieval is not enough 2026-11-04 UTC
Can grassroots contracts make AI platforms more accountable? 2026-11-04 UTC
SumOne Trains a Small Model to Condense AI Agent Histories 2026-11-04 UTC
A New Way to Shrink What AI Agents Read from Their Tools 2026-11-04 UTC
A Preprint Proposes Turning AI Agents’ Past Attempts Into Training Rubrics 2026-11-04 UTC
A proposed scheduling layer separates AI agents’ urgent work from lasting changes 2026-11-04 UTC
GraphRail checks whether search agents’ reasoning stays grounded in evidence 2026-11-04 UTC
LifeVal tests whether AI assistants can turn personal context into completed tasks 2026-11-04 UTC
FrontierPhysics tests whether AI agents can complete physics research—not just solve problems 2026-11-04 UTC

Previous window · 3 articles

AI agent combines executable skills for clinical genomic analysis 2026-10-29 UTC
A probe flags impending AI-agent leaks, but struggles to identify violations 2026-10-29 UTC
AI agents test quantum-spin predictions and flag a drifting signal 2026-10-29 UTC

preprint Current 37 Previous 0 Change +37

Current window · 37 articles

A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
A Tool Inside the Forward Pass Cuts Text-Calling Costs in Narrow AI Tasks 2026-10-31 UTC
BridgeDock uses unbound protein structures to guide AI molecular docking 2026-10-31 UTC
Beyond Chat History: A Preprint Connects AI Assistants to Persistent Data Engines 2026-10-31 UTC
VCoT-SQL puts AI-generated SQL reasoning through a second check 2026-10-31 UTC
DualClusterNet combines shared mobility patterns with personal context to predict the next place 2026-11-01 UTC
Fármaco AI agent coordinates drug-discovery tools through a shared scientific database 2026-11-02 UTC
AI generated research material faster than teams could collectively evaluate it in a small pilot 2026-11-02 UTC
FITTER combines AI-generated exercise plans with explicit safety checks 2026-11-02 UTC
AI news readers found stock-market signals—but little left to trade at the open 2026-11-02 UTC
EvoML checks machine-learning pipelines in stages and retains successful repairs 2026-11-03 UTC
When a Robot Experiment Becomes Scientific Evidence 2026-11-03 UTC
When 4-Bit AI Models Run Faster—and When the Advantage Disappears 2026-11-03 UTC
H2RB preprint explores how human demonstrations can teach robots new tasks 2026-11-03 UTC
Correct Answers Can Hide an AI Model’s Dependence on Metadata 2026-11-03 UTC
Preprint Finds Hidden Evaluation Errors Can Reshuffle AI Agent Rankings 2026-11-03 UTC
CaliSplat cuts the search cost of Gaussian image compression 2026-11-03 UTC
Language Models Help Tune the Search for Better Satellite Imaging Schedules 2026-11-03 UTC
Financial AI benchmark shows how fact-checking can change the leaderboard 2026-11-03 UTC
Different EEG Models Find Shared Patterns—but Bigger Is Not Always Better 2026-11-03 UTC
Ranking a Whole Feed Without Repeatedly Recomputing Its Contents 2026-11-03 UTC
AI transparency serves builders better than end-users, survey suggests 2026-11-03 UTC
AGORA learns which AI judges to trust when evaluation data is scarce 2026-11-03 UTC
Anduin proposes payment-based reputation for AI-agent marketplaces 2026-11-03 UTC
When ‘Verified’ AI Code Proves Less Than It Seems 2026-11-03 UTC
ViBench 2.0 tests whether AI-built apps still work after the last feature 2026-11-03 UTC
EEG Models May Separate People Better Than the Tasks They Perform 2026-11-03 UTC
AI judges can check the evidence and still follow a false expert cue 2026-11-03 UTC
EnzymeRSI: Improving the Research Workflow, Not Just the Enzyme 2026-11-04 UTC
Can grassroots contracts make AI platforms more accountable? 2026-11-04 UTC
When Compressing AI Context Weakens Refusals 2026-11-04 UTC
EviSeek Gives Embodied AI a Reason to Look Before It Answers 2026-11-04 UTC
SumOne Trains a Small Model to Condense AI Agent Histories 2026-11-04 UTC
A New Way to Shrink What AI Agents Read from Their Tools 2026-11-04 UTC
ElecLoad Puts Events at the Center of Electricity Demand Forecasting 2026-11-04 UTC
A Preprint Proposes Turning AI Agents’ Past Attempts Into Training Rubrics 2026-11-04 UTC
FrontierPhysics tests whether AI agents can complete physics research—not just solve problems 2026-11-04 UTC

language models Current 26 Previous 4 Change +22

Current window · 26 articles

One Token per Creator: A Simpler Route to Generative Recommendations 2026-10-30 UTC
Skill++: Helping AI agents find the right skills as their libraries grow 2026-10-31 UTC
Small language models can learn backdoors without simply copying their teachers 2026-10-31 UTC
A Tool Inside the Forward Pass Cuts Text-Calling Costs in Narrow AI Tasks 2026-10-31 UTC
Unsatz tests whether AI can choose a scientific model—not just fit one 2026-10-31 UTC
EMBERS probes how AI research agents fail when questions and searches change 2026-11-01 UTC
HybridSpec speeds hybrid language models by checking fewer draft tokens 2026-11-02 UTC
Why AI Reasoning Training May Favor Familiar Problems 2026-11-02 UTC
Teaching diffusion models to do more with fewer decoding steps 2026-11-03 UTC
Correct Answers Can Hide an AI Model’s Dependence on Metadata 2026-11-03 UTC
AI Can Fix a Simulated System Without Finding What Broke It 2026-11-03 UTC
Lowering an AI’s Odds of Revealing Personal Data May Not Prove Targeted Protection 2026-11-03 UTC
A simulated city tests whether AI investigators can separate evidence from suspicion 2026-11-03 UTC
LatentTriad screens AI agent skills before they act 2026-11-03 UTC
Different EEG Models Find Shared Patterns—but Bigger Is Not Always Better 2026-11-03 UTC
Can AI agents work with less context? A study tests compact memory and selective reading 2026-11-03 UTC
AI agents may not need every reasoning trace their teachers produce 2026-11-03 UTC
When optimization constraints only work together, can AI spot the group? 2026-11-03 UTC
Text-based decoding cuts errors in a small Hausa medical speech study 2026-11-03 UTC
The Office document you see may not be the one an AI reads 2026-11-04 UTC
EchoKV revisits what an AI model should keep in memory 2026-11-04 UTC
GIST Selects Which Answers—and Which Tokens—to Use in Offline AI Training 2026-11-04 UTC
D3D overlaps drafting and verification to speed up language-model decoding 2026-11-04 UTC
SumOne Trains a Small Model to Condense AI Agent Histories 2026-11-04 UTC
ElecLoad Puts Events at the Center of Electricity Demand Forecasting 2026-11-04 UTC
When grading rules leave gaps, AI can quietly fill them 2026-11-04 UTC

Previous window · 4 articles

A probe flags impending AI-agent leaks, but struggles to identify violations 2026-10-29 UTC
A compact AI model combines when to help with what to suggest 2026-10-29 UTC
Language-model gains may come from diversity, not hidden experts 2026-10-29 UTC
A Wrong Chemistry Answer May Hide a More Structured Internal Representation 2026-10-23 UTC

ai evaluation Current 20 Previous 0 Change +20

Current window · 20 articles

AI Can Write SQL. Making It Trustworthy Takes More Than a Bigger Model 2026-10-30 UTC
Estimating AI Reliability From Fewer Repeated Trials 2026-10-31 UTC
When Can Fast Decision Models Replace LLM Judges? 2026-10-31 UTC
When AI Conversations Go Off Track, Rebuilding Context Can Help 2026-10-31 UTC
LadderRAG Searches Across Book Chapters—But Better Retrieval Is Only Half the Story 2026-10-31 UTC
RAGLog looks for hidden faults behind AI-generated answers 2026-11-01 UTC
Could the shape of word connections help evaluate AI reasoning? 2026-11-02 UTC
AI Can Fix a Simulated System Without Finding What Broke It 2026-11-03 UTC
Specialist AI assistants do not always give better regulatory answers 2026-11-03 UTC
A simulated city tests whether AI investigators can separate evidence from suspicion 2026-11-03 UTC
When AI Agents Change Without Getting Better 2026-11-03 UTC
AGORA learns which AI judges to trust when evaluation data is scarce 2026-11-03 UTC
Bio-VQA exposes the fine-detail limits of vision-language models in biology 2026-11-03 UTC
AI judges can check the evidence and still follow a false expert cue 2026-11-03 UTC
PersonaCodeBench tests whether coding agents meet users’ needs as well as pass tests 2026-11-03 UTC
Expert Feedback Helps AI Refine Finance Briefs—but Strong Answers Can Get Worse 2026-11-03 UTC
AI forecasts of freelance-job success improve when models know the agent’s limits 2026-11-03 UTC
GREP asks whether AI-generated rooms actually make sense 2026-11-04 UTC
LifeVal tests whether AI assistants can turn personal context into completed tasks 2026-11-04 UTC
CompressionBench tests whether coding agents can shrink language models without losing usefulness 2026-11-04 UTC

reinforcement learning Current 18 Previous 1 Change +17

Current window · 18 articles

AI Can Write SQL. Making It Trustworthy Takes More Than a Bigger Model 2026-10-30 UTC
OmniPiano tests AI control with up to five virtual piano-playing hands 2026-10-30 UTC
Graph Neural Networks Learn to Group Related Logic Functions 2026-10-30 UTC
A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
EvoMemState gives AI memories context—and rules for using it 2026-11-02 UTC
Why AI Reasoning Training May Favor Familiar Problems 2026-11-02 UTC
AlgoPilot teaches language models to choose a solving strategy before answering 2026-11-02 UTC
Harness-S trains AI agents to retain lessons from specialized execution support 2026-11-03 UTC
Teaching a live jamming detector with hindsight 2026-11-03 UTC
FourSight targets concentrated errors to stabilize four-bit AI training 2026-11-03 UTC
WebCatalyst trains HTML generators to improve what happens after the first click 2026-11-03 UTC
Teaching AI when to ask another question—and when to stop 2026-11-03 UTC
OdorSpaces tests how virtual robots can trace hidden gas leaks and fires 2026-11-03 UTC
Teaching vision transformers where finer image patches matter 2026-11-03 UTC
Teaching Alexa+ Icon AI to Leave Room Between the Lines 2026-11-04 UTC
ModalSearcher trains AI agents to decide when a search needs images 2026-11-04 UTC
Better Questions, Better Legal Predictions? Inside LegalEvolver 2026-11-04 UTC
A Preprint Proposes Turning AI Agents’ Past Attempts Into Training Rubrics 2026-11-04 UTC

Previous window · 1 articles

Accurate plasma forecasts do not guarantee reliable tokamak control 2026-10-27 UTC

artificial intelligence Current 13 Previous 2 Change +11

Current window · 13 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
A Portable AI Memory Layer Transfers Some Learned Skills Without Retraining 2026-10-30 UTC
A Tool Inside the Forward Pass Cuts Text-Calling Costs in Narrow AI Tasks 2026-10-31 UTC
Beyond Chat History: A Preprint Connects AI Assistants to Persistent Data Engines 2026-10-31 UTC
AI news readers found stock-market signals—but little left to trade at the open 2026-11-02 UTC
A learned token can hide unwanted AI behavior—but does not erase it 2026-11-03 UTC
AI Can Fix a Simulated System Without Finding What Broke It 2026-11-03 UTC
Teaching AI When to Stop Reasoning 2026-11-03 UTC
Can Rewritten Captions Make an AI Stop Recognizing a Face? 2026-11-03 UTC
HTCE gives navigation AI a simpler way to reuse past routes 2026-11-03 UTC
When ‘Verified’ AI Code Proves Less Than It Seems 2026-11-03 UTC
When AI agents change, should their permissions change too? 2026-11-03 UTC
A relevance rule for combining expert knowledge maps 2026-11-03 UTC

Previous window · 2 articles

AI agent combines executable skills for clinical genomic analysis 2026-10-29 UTC
AI agent estimates crop losses from extreme weather in Florida 2026-10-29 UTC

vision-language models Current 11 Previous 1 Change +10

Current window · 11 articles

VagueBench tests why embodied AI agents struggle with shorter instructions 2026-11-02 UTC
Teaching diffusion models to do more with fewer decoding steps 2026-11-03 UTC
Can Rewritten Captions Make an AI Stop Recognizing a Face? 2026-11-03 UTC
HTCE gives navigation AI a simpler way to reuse past routes 2026-11-03 UTC
Bio-VQA exposes the fine-detail limits of vision-language models in biology 2026-11-03 UTC
Reading a Chart Accurately Did Not Guarantee Better AI Decisions 2026-11-03 UTC
GREP asks whether AI-generated rooms actually make sense 2026-11-04 UTC
RECAP reuses context-aware predictions to speed vision-language models 2026-11-04 UTC
UniCompress shrinks a multi-skill vision-language model while recovering most task performance 2026-11-04 UTC
Personalized AI struggles to connect the right memories to the right person 2026-11-04 UTC
EviSeek Gives Embodied AI a Reason to Look Before It Answers 2026-11-04 UTC

Previous window · 1 articles

VeriCUA explores digital environments to check whether agent tasks are complete 2026-10-29 UTC

multi-agent systems Current 8 Previous 2 Change +6

Current window · 8 articles

PatchScout tackles web research by deciding when to move on 2026-10-30 UTC
FITTER combines AI-generated exercise plans with explicit safety checks 2026-11-02 UTC
EvoML checks machine-learning pipelines in stages and retains successful repairs 2026-11-03 UTC
Coordinated AI agents improve vulnerability exploitation in controlled benchmarks 2026-11-03 UTC
Keeping AI agents within their assigned authority 2026-11-03 UTC
When AI Agents Influence Each Other, Deception Wins in New Tests 2026-11-03 UTC
Training a web agent’s planner and actor together improves benchmark success 2026-11-03 UTC
MA-Mesh Gives AI Agent Teams a Way to Review and Replace Failing Peers 2026-11-04 UTC

Previous window · 2 articles

AI agents propose useful experiments, but choosing the best remains harder 2026-10-29 UTC
A probe flags impending AI-agent leaks, but struggles to identify violations 2026-10-29 UTC

reproducibility Current 8 Previous 0 Change +8

Current window · 8 articles

Exact Replay Does Not Guarantee Stable AI Deliberation 2026-10-31 UTC
A Zero-Starting Gate for Adding Non-Text Inputs to Frozen Language Models 2026-10-31 UTC
When an AI experiment’s frozen protocol needs a bug fix 2026-11-03 UTC
When a Robot Experiment Becomes Scientific Evidence 2026-11-03 UTC
Preprint Finds Hidden Evaluation Errors Can Reshuffle AI Agent Rankings 2026-11-03 UTC
LLM game characters: a research map reveals gaps in speed, safety and memory 2026-11-02 UTC
AI feedback lifts data-science project scores—but the judge matters 2026-11-03 UTC
Why AI failure explanations need a replay test, researchers argue 2026-11-03 UTC

retrieval-augmented generation Current 8 Previous 0 Change +8

Current window · 8 articles

Better Context Helps a Smaller AI Answer Questions About Scientific Figures 2026-10-30 UTC
AI agents organize thermoelectric research records—and reveal why traceability matters 2026-10-31 UTC
LadderRAG Searches Across Book Chapters—But Better Retrieval Is Only Half the Story 2026-10-31 UTC
RAGLog looks for hidden faults behind AI-generated answers 2026-11-01 UTC
A Stock-News RAG Prototype Reports Fast Answers, but Accuracy Remains an Open Question 2026-11-02 UTC
Query-Matching Documents Can Crowd Out Evidence in RAG Retrieval 2026-11-03 UTC
Specialist AI assistants do not always give better regulatory answers 2026-11-03 UTC
When graphs help AI agents—and why better retrieval is not enough 2026-11-04 UTC

ai safety Current 7 Previous 1 Change +6

Current window · 7 articles

When AI Gets the Score Right but the Work Wrong 2026-10-30 UTC
Could the shape of word connections help evaluate AI reasoning? 2026-11-02 UTC
Correct Answers Can Hide an AI Model’s Dependence on Metadata 2026-11-03 UTC
When AI Agents Influence Each Other, Deception Wins in New Tests 2026-11-03 UTC
ScamWorld tests whether AI web agents stop before a fraudulent payment 2026-11-03 UTC
SafeStart targets the safety cost of running fewer AI experts 2026-11-04 UTC
Temporarily disabling safety neurons could make AI models harder to jailbreak 2026-11-04 UTC

Previous window · 1 articles

A probe flags impending AI-agent leaks, but struggles to identify violations 2026-10-29 UTC

multimodal ai Current 7 Previous 0 Change +7

Current window · 7 articles

Better Context Helps a Smaller AI Answer Questions About Scientific Figures 2026-10-30 UTC
Combining biopsy images and clinical data: no single AI method wins across bowel disease outcomes 2026-11-03 UTC
RECAP reuses context-aware predictions to speed vision-language models 2026-11-04 UTC
ScamCourt tests whether AI can distinguish scam videos from convincing look-alikes 2026-11-04 UTC
ModalSearcher trains AI agents to decide when a search needs images 2026-11-04 UTC
Personalized AI struggles to connect the right memories to the right person 2026-11-04 UTC
A New Benchmark Tests Whether AI Can Rebuild Documents as Editable HTML 2026-11-04 UTC

research preprint Current 7 Previous 0 Change +7

Current window · 7 articles

Evidence-trained AI helps design a better contact for perovskite solar cells 2026-10-31 UTC
Can a Small Selector Learn Which Examples Help a Language Model? 2026-10-31 UTC
Small language models can learn backdoors without simply copying their teachers 2026-10-31 UTC
LadderRAG Searches Across Book Chapters—But Better Retrieval Is Only Half the Story 2026-10-31 UTC
For AI Research Agents, Naming an Experiment Is Not Designing One 2026-10-31 UTC
A Small AI Model Tests a More Inspectable Way to Make Research Decisions 2026-10-31 UTC
MemSidecar puts AI memory retrieval on a separate track 2026-10-31 UTC

agent memory Current 6 Previous 0 Change +6

Current window · 6 articles

MemSidecar puts AI memory retrieval on a separate track 2026-10-31 UTC
When AI Agents Change Without Getting Better 2026-11-03 UTC
AI Research Agents With Memory Start Faster—but Do Not Reliably Finish Better 2026-11-03 UTC
AI agents remember useful lessons—but struggle to keep them current 2026-11-03 UTC
When graphs help AI agents—and why better retrieval is not enough 2026-11-04 UTC
SumOne Trains a Small Model to Condense AI Agent Histories 2026-11-04 UTC

coding agents Current 6 Previous 0 Change +6

Current window · 6 articles

Training an AI Draft Model to Disagree at Crucial Moments 2026-11-03 UTC
PersonaCodeBench tests whether coding agents meet users’ needs as well as pass tests 2026-11-03 UTC
DARE looks beyond coding-agent scores to diagnose repair difficulty 2026-11-04 UTC
HarnessFlow searches for better AI-agent software without changing the model 2026-11-04 UTC
ServerBench tests whether coding agents can build better LLM serving systems 2026-11-04 UTC
CompressionBench tests whether coding agents can shrink language models without losing usefulness 2026-11-04 UTC

direct preference optimization Current 6 Previous 0 Change +6

Current window · 6 articles

AdKnob gives AI-generated advertising an intensity dial—and a way to mark it 2026-10-31 UTC
Correct Answers Can Hide an AI Model’s Dependence on Metadata 2026-11-03 UTC
Teaching AI When to Stop Reasoning 2026-11-03 UTC
Choosing Which AI Preferences to Label—and When Disagreement Helps 2026-11-03 UTC
Who Gets to Shape AI? The Case for Distributed Alignment 2026-11-04 UTC
Temporarily disabling safety neurons could make AI models harder to jailbreak 2026-11-04 UTC

inference efficiency Current 6 Previous 0 Change +6

Current window · 6 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
A Tool Inside the Forward Pass Cuts Text-Calling Costs in Narrow AI Tasks 2026-10-31 UTC
Can AI agents work with less context? A study tests compact memory and selective reading 2026-11-03 UTC
Ranking a Whole Feed Without Repeatedly Recomputing Its Contents 2026-11-03 UTC
Teaching vision transformers where finer image patches matter 2026-11-03 UTC
RECAP reuses context-aware predictions to speed vision-language models 2026-11-04 UTC

knowledge distillation Current 6 Previous 0 Change +6

Current window · 6 articles

Compressing Small Language Models: When Combining Techniques Helps—and When It Fails 2026-10-30 UTC
Can a Small Selector Learn Which Examples Help a Language Model? 2026-10-31 UTC
Small language models can learn backdoors without simply copying their teachers 2026-10-31 UTC
Teaching diffusion models to do more with fewer decoding steps 2026-11-03 UTC
AI agents may not need every reasoning trace their teachers produce 2026-11-03 UTC
UniCompress shrinks a multi-skill vision-language model while recovering most task performance 2026-11-04 UTC

speculative decoding Current 6 Previous 1 Change +5

Current window · 6 articles

HybridSpec speeds hybrid language models by checking fewer draft tokens 2026-11-02 UTC
Training an AI Draft Model to Disagree at Crucial Moments 2026-11-03 UTC
Hybrid Spark pairs prediction with copying to speed up AI code editing 2026-11-03 UTC
RECAP reuses context-aware predictions to speed vision-language models 2026-11-04 UTC
Split-KV speeds diffusion drafter training by keeping long-context data local 2026-11-04 UTC
D3D overlaps drafting and verification to speed up language-model decoding 2026-11-04 UTC

Previous window · 1 articles

TextSeal2 aims to preserve AI text watermarks during faster decoding 2026-10-29 UTC

synthetic training data Current 6 Previous 0 Change +6

Current window · 6 articles

AuroraWorld turns outside-camera footage into synthetic robot-eye videos 2026-10-30 UTC
VCoT-SQL puts AI-generated SQL reasoning through a second check 2026-10-31 UTC
Choosing Less-Repetitive Training Data Could Make AI Fine-Tuning More Efficient 2026-11-02 UTC
Learning Payment Fraud Sequences to Train Better Detectors 2026-11-03 UTC
CoCo turns textual context into numerical guidance for time-series forecasts 2026-11-03 UTC
ARC-AGI-2 study finds better scheduling and memory use matter more than extra synthetic training 2026-11-04 UTC

world models Current 6 Previous 0 Change +6

Current window · 6 articles

AuroraWorld turns outside-camera footage into synthetic robot-eye videos 2026-10-30 UTC
X-World 1.6: Turning Recorded Streets into Controllable Driving Simulations 2026-10-31 UTC
Rebalancing the vision-to-action interface improves robot task success in a preprint 2026-11-02 UTC
An AI model explores what-if futures for power engineering research 2026-11-03 UTC
Reading physics from an AI model does not mean being able to control it 2026-11-03 UTC
NVIDIA adapts Cosmos models for interactive robot and driving simulation 2026-11-04 UTC

personalization Current 5 Previous 0 Change +5

Current window · 5 articles

DualClusterNet combines shared mobility patterns with personal context to predict the next place 2026-11-01 UTC
EvoMemState gives AI memories context—and rules for using it 2026-11-02 UTC
CogniLife proposes a way for AI experts to learn from their creators 2026-11-03 UTC
PersonaCodeBench tests whether coding agents meet users’ needs as well as pass tests 2026-11-03 UTC
LifeVal tests whether AI assistants can turn personal context into completed tasks 2026-11-04 UTC

tool use Current 5 Previous 0 Change +5

Current window · 5 articles

When AI Conversations Go Off Track, Rebuilding Context Can Help 2026-10-31 UTC
A Tool Inside the Forward Pass Cuts Text-Calling Costs in Narrow AI Tasks 2026-10-31 UTC
Harness-S trains AI agents to retain lessons from specialized execution support 2026-11-03 UTC
Signals: Diagnosing AI Agents Beyond Successful Tool Calls 2026-11-03 UTC
A New Way to Shrink What AI Agents Read from Their Tools 2026-11-04 UTC

vision-language-action models Current 5 Previous 0 Change +5

Current window · 5 articles

Editing a Robot Model’s Hidden Goal Without Changing Its Instructions 2026-10-31 UTC
Rebalancing the vision-to-action interface improves robot task success in a preprint 2026-11-02 UTC
AceAction maps the steps between game instructions and player actions 2026-11-03 UTC
H2RB preprint explores how human demonstrations can teach robots new tasks 2026-11-03 UTC
MESA tests where robot skills stop generalizing 2026-11-03 UTC

activation steering Current 4 Previous 0 Change +4

Current window · 4 articles

Editing a Robot Model’s Hidden Goal Without Changing Its Instructions 2026-10-31 UTC
LoRA-Patch steers model activations to weaken backdoored adapters 2026-11-02 UTC
ATLAS steers AI agents’ hidden states to reduce coordination drift 2026-11-03 UTC
When One Steering Direction Is Not Enough for a Language Model 2026-11-03 UTC

ai governance Current 4 Previous 0 Change +4

Current window · 4 articles

More AI Records, Harder Comparisons: How Federal Inventories Rewrite Accountability 2026-11-03 UTC
AI transparency serves builders better than end-users, survey suggests 2026-11-03 UTC
Who Gets to Shape AI? The Case for Distributed Alignment 2026-11-04 UTC
Can grassroots contracts make AI platforms more accountable? 2026-11-04 UTC

ai security Current 4 Previous 0 Change +4

Current window · 4 articles

Small language models can learn backdoors without simply copying their teachers 2026-10-31 UTC
Evolving poisoned search results can mislead AI agents—or make them stop answering 2026-11-02 UTC
A fixed answer menu does not stop AI decisions from being steered 2026-11-02 UTC
The Office document you see may not be the one an AI reads 2026-11-04 UTC

benchmarking Current 4 Previous 1 Change +3

Current window · 4 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
MemU-Bench tests whether AI phone assistants can remember what users leave unsaid 2026-10-30 UTC
Specialist AI assistants do not always give better regulatory answers 2026-11-03 UTC
SlackBench tests whether AI agents can piece together a collaborative project 2026-11-03 UTC

Previous window · 1 articles

VeriCUA explores digital environments to check whether agent tasks are complete 2026-10-29 UTC

code generation Current 4 Previous 0 Change +4

Current window · 4 articles

One AI can plan the program while another writes the code 2026-11-03 UTC
Teaching AI When to Stop Reasoning 2026-11-03 UTC
WebCatalyst trains HTML generators to improve what happens after the first click 2026-11-03 UTC
When AI coding models spend their entire output budget reasoning 2026-11-04 UTC

continual learning Current 4 Previous 0 Change +4

Current window · 4 articles

Exo lets AI agents rewrite their harness while working 2026-10-30 UTC
Skill++: Helping AI agents find the right skills as their libraries grow 2026-10-31 UTC
WASP-Mem preprint tests wiki-style memory for workplace AI agents 2026-11-02 UTC
AI Research Agents With Memory Start Faster—but Do Not Reliably Finish Better 2026-11-03 UTC

diffusion models Current 4 Previous 0 Change +4

Current window · 4 articles

AuroraWorld turns outside-camera footage into synthetic robot-eye videos 2026-10-30 UTC
AI edits cell-nucleus images while separating gene and shape signals 2026-10-30 UTC
MA-SafeDiffuser adds safety checks to multi-agent diffusion planning 2026-11-03 UTC
DyPSI learns to predict physical fields and plan sensor paths together 2026-11-04 UTC

embodied ai Current 4 Previous 1 Change +3

Current window · 4 articles

VagueBench tests why embodied AI agents struggle with shorter instructions 2026-11-02 UTC
When a Robot Experiment Becomes Scientific Evidence 2026-11-03 UTC
HTCE gives navigation AI a simpler way to reuse past routes 2026-11-03 UTC
BEAKER benchmark reveals a gap between understanding lab scenes and locating where to act 2026-11-04 UTC

Previous window · 1 articles

AI coding agents build a robotics simulation benchmark 2026-10-29 UTC

generative ai Current 4 Previous 0 Change +4

Current window · 4 articles

BrainGFM uses synthetic scans to stretch scarce brain-imaging data 2026-10-30 UTC
CAST-Bench tests whether AI-generated sounds belong to the right scene and speaker 2026-11-02 UTC
AI transparency serves builders better than end-users, survey suggests 2026-11-03 UTC
Tailored Evidence, Not Just Conversation, May Explain AI’s Effect on Conspiracy Beliefs 2026-11-03 UTC

jev Current 4 Previous 0 Change +4

Current window · 4 articles

When Can Fast Decision Models Replace LLM Judges? 2026-10-31 UTC
Can a Small Selector Learn Which Examples Help a Language Model? 2026-10-31 UTC
Structured Clinical Memory Shows Modest Gains in a Synthetic AI Decision Benchmark 2026-11-03 UTC
Fast, Cheap—and Fair? A Recruitment AI Audit Finds Different Answers 2026-11-03 UTC

llm-as-a-judge Current 4 Previous 0 Change +4

Current window · 4 articles

Matching Score Distributions Could Help AI Judges Align With Human Ratings 2026-10-30 UTC
When Can Fast Decision Models Replace LLM Judges? 2026-10-31 UTC
AI feedback lifts data-science project scores—but the judge matters 2026-11-03 UTC
AGORA learns which AI judges to trust when evaluation data is scarce 2026-11-03 UTC

mechanistic interpretability Current 4 Previous 0 Change +4

Current window · 4 articles

A Transformer’s Arithmetic Circuit Works Despite Local Geometric Distortion 2026-10-30 UTC
Editing a Robot Model’s Hidden Goal Without Changing Its Instructions 2026-10-31 UTC
Lowering an AI’s Odds of Revealing Personal Data May Not Prove Targeted Protection 2026-11-03 UTC
Can an AI Model Forget—or Just Stop Answering? 2026-11-03 UTC

mixture of experts Current 4 Previous 0 Change +4

Current window · 4 articles

HybridSpec speeds hybrid language models by checking fewer draft tokens 2026-11-02 UTC
Proving GPU Kernel Correctness in Lean—Within Explicit Limits 2026-11-03 UTC
DGC-Net Uses Cross-Modal Context to Weigh Sentiment Cues in Video 2026-11-03 UTC
ARC-AGI-2 study finds better scheduling and memory use matter more than extra synthetic training 2026-11-04 UTC

quantization Current 4 Previous 0 Change +4

Current window · 4 articles

Compressing Small Language Models: When Combining Techniques Helps—and When It Fails 2026-10-30 UTC
When 4-Bit AI Models Run Faster—and When the Advantage Disappears 2026-11-03 UTC
FourSight targets concentrated errors to stabilize four-bit AI training 2026-11-03 UTC
CompressionBench tests whether coding agents can shrink language models without losing usefulness 2026-11-04 UTC

reasoning models Current 4 Previous 0 Change +4

Current window · 4 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
Teaching AI When to Stop Reasoning 2026-11-03 UTC
ConceptARC-100 tests how consistently reasoning models apply abstract rules 2026-11-04 UTC
ARC-AGI-2 study finds better scheduling and memory use matter more than extra synthetic training 2026-11-04 UTC

recommender systems Current 4 Previous 0 Change +4

Current window · 4 articles

DualClusterNet combines shared mobility patterns with personal context to predict the next place 2026-11-01 UTC
More platforms do not guarantee better AI recommendations 2026-11-03 UTC
Ranking a Whole Feed Without Repeatedly Recomputing Its Contents 2026-11-03 UTC
Taobao researchers recycle unseen recommendations to broaden video discovery 2026-11-04 UTC

recursive self-improvement Current 4 Previous 1 Change +3

Current window · 4 articles

Recursa improves AI legal research by revising its own working knowledge 2026-11-02 UTC
Reglos separates learning a user’s preferences from improving how AI uses memory 2026-11-04 UTC
EnzymeRSI: Improving the Research Workflow, Not Just the Enzyme 2026-11-04 UTC
CompressionBench tests whether coding agents can shrink language models without losing usefulness 2026-11-04 UTC

Previous window · 1 articles

RSI-Dojo trains AI agents to improve other language models 2026-10-29 UTC

text-to-sql Current 4 Previous 0 Change +4

Current window · 4 articles

AI Can Write SQL. Making It Trustworthy Takes More Than a Bigger Model 2026-10-30 UTC
Physicians preferred conversational database queries, but accuracy remained a concern 2026-10-31 UTC
Beyond Chat History: A Preprint Connects AI Assistants to Persistent Data Engines 2026-10-31 UTC
VCoT-SQL puts AI-generated SQL reasoning through a second check 2026-10-31 UTC

agent harnesses Current 3 Previous 0 Change +3

Current window · 3 articles

Exo lets AI agents rewrite their harness while working 2026-10-30 UTC
Harness-S trains AI agents to retain lessons from specialized execution support 2026-11-03 UTC
SlackBench tests whether AI agents can piece together a collaborative project 2026-11-03 UTC

ai alignment Current 3 Previous 0 Change +3

Current window · 3 articles

When community beliefs steer AI toward cooperation—or free-riding 2026-11-02 UTC
A learned token can hide unwanted AI behavior—but does not erase it 2026-11-03 UTC
When Does Poor AI Performance Become Catastrophic? 2026-11-04 UTC

ai benchmarks Current 3 Previous 1 Change +2

Current window · 3 articles

Financial AI benchmark shows how fact-checking can change the leaderboard 2026-11-03 UTC
AI agents remember useful lessons—but struggle to keep them current 2026-11-03 UTC
Personalized AI struggles to connect the right memories to the right person 2026-11-04 UTC

Previous window · 1 articles

LOLPlay tests whether visual AI agents can keep up with League of Legends 2026-10-25 UTC

ai memory Current 3 Previous 0 Change +3

Current window · 3 articles

CogniLife proposes a way for AI experts to learn from their creators 2026-11-03 UTC
An AI memory proposal would preserve organizational judgments—not just records 2026-11-03 UTC
Reglos separates learning a user’s preferences from improving how AI uses memory 2026-11-04 UTC

ai reliability Current 3 Previous 0 Change +3

Current window · 3 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
When AI learns new facts, its confidence may lag behind 2026-11-03 UTC
Choosing each next move can improve AI agents—but uses far more tokens 2026-11-04 UTC

ai research agents Current 3 Previous 1 Change +2

Current window · 3 articles

For AI Research Agents, Naming an Experiment Is Not Designing One 2026-10-31 UTC
EMBERS probes how AI research agents fail when questions and searches change 2026-11-01 UTC
AI Research Agents With Memory Start Faster—but Do Not Reliably Finish Better 2026-11-03 UTC

Previous window · 1 articles

AI agents propose useful experiments, but choosing the best remains harder 2026-10-29 UTC

ai-assisted research Current 3 Previous 0 Change +3

Current window · 3 articles

AI-guided plasma simulations separate stronger heating from brighter X-rays 2026-11-01 UTC
AI generated research material faster than teams could collectively evaluate it in a small pilot 2026-11-02 UTC
A Checkable Proof of the Best Solution to One Optimization Benchmark 2026-11-03 UTC

autonomous driving Current 3 Previous 0 Change +3

Current window · 3 articles

X-World 1.6: Turning Recorded Streets into Controllable Driving Simulations 2026-10-31 UTC
Jev-AD tests whether looking two seconds ahead improves language-guided driving 2026-11-03 UTC
NVIDIA adapts Cosmos models for interactive robot and driving simulation 2026-11-04 UTC

causal inference Current 3 Previous 0 Change +3

Current window · 3 articles

AI Can Fix a Simulated System Without Finding What Broke It 2026-11-03 UTC
Why AI failure explanations need a replay test, researchers argue 2026-11-03 UTC
Tracing Individual Causal Effects With Petri Nets 2026-11-03 UTC

chain of thought Current 3 Previous 0 Change +3

Current window · 3 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
Could the shape of word connections help evaluate AI reasoning? 2026-11-02 UTC
A layer-by-layer merging method aims to shorten AI reasoning without retraining 2026-11-02 UTC

context compression Current 3 Previous 0 Change +3

Current window · 3 articles

When Compressing AI Context Weakens Refusals 2026-11-04 UTC
SumOne Trains a Small Model to Condense AI Agent Histories 2026-11-04 UTC
A New Way to Shrink What AI Agents Read from Their Tools 2026-11-04 UTC

credit assignment Current 3 Previous 0 Change +3

Current window · 3 articles

A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
WebCatalyst trains HTML generators to improve what happens after the first click 2026-11-03 UTC
A Preprint Proposes Turning AI Agents’ Past Attempts Into Training Rubrics 2026-11-04 UTC

decision models Current 3 Previous 0 Change +3

Current window · 3 articles

Trail turns smart home commands into constrained local decisions 2026-10-31 UTC
A fixed answer menu does not stop AI decisions from being steered 2026-11-02 UTC
Fast, Cheap—and Fair? A Recruitment AI Audit Finds Different Answers 2026-11-03 UTC

distributed training Current 3 Previous 0 Change +3

Current window · 3 articles

FP4Quant speeds up GPU communication, with a measurable accuracy trade-off 2026-11-03 UTC
AMD researchers accelerate training workloads by keeping GPU data moving 2026-11-03 UTC
Split-KV speeds diffusion drafter training by keeping long-context data local 2026-11-04 UTC

earth observation Current 3 Previous 0 Change +3

Current window · 3 articles

A two-stage reasoning system helps AI choose Earth-observation evidence 2026-11-03 UTC
Language Models Help Tune the Search for Better Satellite Imaging Schedules 2026-11-03 UTC
CARM adapts trust masks as scientific super-resolution data change 2026-11-04 UTC

eeg Current 3 Previous 0 Change +3

Current window · 3 articles

Different EEG Models Find Shared Patterns—but Bigger Is Not Always Better 2026-11-03 UTC
BrainBind compares EEG and fMRI video retrieval—and exposes limits on unseen episodes 2026-11-03 UTC
EEG Models May Separate People Better Than the Tasks They Perform 2026-11-03 UTC

evidence provenance Current 3 Previous 0 Change +3

Current window · 3 articles

AR Glasses That Remember Encounters—and Keep the Images Behind Their Answers 2026-11-03 UTC
TACT puts an AI council to work on qualitative data—with humans retaining judgment 2026-11-03 UTC
An AI memory proposal would preserve organizational judgments—not just records 2026-11-03 UTC

experimental design Current 3 Previous 0 Change +3

Current window · 3 articles

For AI Research Agents, Naming an Experiment Is Not Designing One 2026-10-31 UTC
Unsatz tests whether AI can choose a scientific model—not just fit one 2026-10-31 UTC
AI Can Fix a Simulated System Without Finding What Broke It 2026-11-03 UTC

fine-tuning Current 3 Previous 0 Change +3

Current window · 3 articles

A Portable AI Memory Layer Transfers Some Learned Skills Without Retraining 2026-10-30 UTC
Correct Answers Can Hide an AI Model’s Dependence on Metadata 2026-11-03 UTC
When AI learns new facts, its confidence may lag behind 2026-11-03 UTC

flow matching Current 3 Previous 0 Change +3

Current window · 3 articles

A discrete-time bridge between deterministic diffusion and flow matching 2026-10-31 UTC
Learning to reconstruct single-pixel video from noisy-looking feedback 2026-11-01 UTC
Keeping spectral graph generation within mathematical constraints 2026-11-03 UTC

formal verification Current 3 Previous 0 Change +3

Current window · 3 articles

Proving GPU Kernel Correctness in Lean—Within Explicit Limits 2026-11-03 UTC
When ‘Verified’ AI Code Proves Less Than It Seems 2026-11-03 UTC
When grading rules leave gaps, AI can quietly fill them 2026-11-04 UTC

foundation models Current 3 Previous 0 Change +3

Current window · 3 articles

Recursa improves AI legal research by revising its own working knowledge 2026-11-02 UTC
Different EEG Models Find Shared Patterns—but Bigger Is Not Always Better 2026-11-03 UTC
EEG Models May Separate People Better Than the Tasks They Perform 2026-11-03 UTC

grpo Current 3 Previous 0 Change +3

Current window · 3 articles

A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
Training a web agent’s planner and actor together improves benchmark success 2026-11-03 UTC
A Preprint Proposes Turning AI Agents’ Past Attempts Into Training Rubrics 2026-11-04 UTC

hidden states Current 3 Previous 0 Change +3

Current window · 3 articles

Unsatz tests whether AI can choose a scientific model—not just fit one 2026-10-31 UTC
When One Steering Direction Is Not Enough for a Language Model 2026-11-03 UTC
LatentTriad screens AI agent skills before they act 2026-11-03 UTC

human-ai collaboration Current 3 Previous 0 Change +3

Current window · 3 articles

BrainGFM uses synthetic scans to stretch scarce brain-imaging data 2026-10-30 UTC
AI generated research material faster than teams could collectively evaluate it in a small pilot 2026-11-02 UTC
Expert Feedback Helps AI Refine Finance Briefs—but Strong Answers Can Get Worse 2026-11-03 UTC

knowledge graphs Current 3 Previous 0 Change +3

Current window · 3 articles

A relevance rule for combining expert knowledge maps 2026-11-03 UTC
When graphs help AI agents—and why better retrieval is not enough 2026-11-04 UTC
GraphRail checks whether search agents’ reasoning stays grounded in evidence 2026-11-04 UTC

llm serving Current 3 Previous 0 Change +3

Current window · 3 articles

AMD’s InferaSim aims to cut the GPU cost of tuning LLM serving 2026-11-02 UTC
When 4-Bit AI Models Run Faster—and When the Advantage Disappears 2026-11-03 UTC
ServerBench tests whether coding agents can build better LLM serving systems 2026-11-04 UTC

long-term memory Current 3 Previous 0 Change +3

Current window · 3 articles

MemU-Bench tests whether AI phone assistants can remember what users leave unsaid 2026-10-30 UTC
AI memory is useful only when it helps with the task at hand 2026-11-02 UTC
Training AI Agents to Remember—and Check Their Memories 2026-11-03 UTC

lora Current 3 Previous 0 Change +3

Current window · 3 articles

Compressing Small Language Models: When Combining Techniques Helps—and When It Fails 2026-10-30 UTC
Training AI Agents to Remember—and Check Their Memories 2026-11-03 UTC
UniCompress shrinks a multi-skill vision-language model while recovering most task performance 2026-11-04 UTC

mathematical reasoning Current 3 Previous 0 Change +3

Current window · 3 articles

A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
A layer-by-layer merging method aims to shorten AI reasoning without retraining 2026-11-02 UTC
Teaching AI When to Stop Reasoning 2026-11-03 UTC

memory retrieval Current 3 Previous 0 Change +3

Current window · 3 articles

EvoMemState gives AI memories context—and rules for using it 2026-11-02 UTC
Could internal rhythms give AI a different way to process time? 2026-11-03 UTC
Reglos separates learning a user’s preferences from improving how AI uses memory 2026-11-04 UTC

mixture-of-experts Current 3 Previous 0 Change +3

Current window · 3 articles

Switching Off AI Experts Can Break More Than Routing 2026-11-04 UTC
Steering AI’s internal routers to cut repetitive reasoning 2026-11-04 UTC
SafeStart targets the safety cost of running fewer AI experts 2026-11-04 UTC

model compression Current 3 Previous 0 Change +3

Current window · 3 articles

Compressing Small Language Models: When Combining Techniques Helps—and When It Fails 2026-10-30 UTC
TopoQuant probes how compression changes language models’ attention 2026-10-31 UTC
UniCompress shrinks a multi-skill vision-language model while recovering most task performance 2026-11-04 UTC

open-weight models Current 3 Previous 0 Change +3

Current window · 3 articles

Coordinated AI agents improve vulnerability exploitation in controlled benchmarks 2026-11-03 UTC
When AI coding models spend their entire output budget reasoning 2026-11-04 UTC
Temporarily disabling safety neurons could make AI models harder to jailbreak 2026-11-04 UTC

pre-registration Current 3 Previous 0 Change +3

Current window · 3 articles

When an AI experiment’s frozen protocol needs a bug fix 2026-11-03 UTC
Stricter AI checks did not consistently improve research results in two tests 2026-11-03 UTC
Reading physics from an AI model does not mean being able to control it 2026-11-03 UTC

prompt injection Current 3 Previous 0 Change +3

Current window · 3 articles

When Can Fast Decision Models Replace LLM Judges? 2026-10-31 UTC
A fixed answer menu does not stop AI decisions from being steered 2026-11-02 UTC
LatentTriad screens AI agent skills before they act 2026-11-03 UTC

research evaluation Current 3 Previous 1 Change +2

Current window · 3 articles

A Proposal to Connect AI Laboratories Through Shared Scientific Memory 2026-10-31 UTC
AI literature reviews: better access helps, but expert judgment still matters 2026-11-03 UTC
FrontierPhysics tests whether AI agents can complete physics research—not just solve problems 2026-11-04 UTC

Previous window · 1 articles

AI agents propose useful experiments, but choosing the best remains harder 2026-10-29 UTC

resource allocation Current 3 Previous 0 Change +3

Current window · 3 articles

TAILOR targets the risky tail of AI-generated computer-system heuristics 2026-10-31 UTC
A safer way to refine wireless schedules before the clock runs out 2026-11-04 UTC
RAGAM-AI uses language-model feedback to guide edge resource allocation 2026-11-04 UTC

robot learning Current 3 Previous 1 Change +2

Current window · 3 articles

AuroraWorld turns outside-camera footage into synthetic robot-eye videos 2026-10-30 UTC
Rebalancing the vision-to-action interface improves robot task success in a preprint 2026-11-02 UTC
H2RB preprint explores how human demonstrations can teach robots new tasks 2026-11-03 UTC

Previous window · 1 articles

AI coding agents build a robotics simulation benchmark 2026-10-29 UTC

robotic manipulation Current 3 Previous 0 Change +3

Current window · 3 articles

VagueBench tests why embodied AI agents struggle with shorter instructions 2026-11-02 UTC
Rebalancing the vision-to-action interface improves robot task success in a preprint 2026-11-02 UTC
MESA tests where robot skills stop generalizing 2026-11-03 UTC

software engineering Current 3 Previous 0 Change +3

Current window · 3 articles

AI coding agents can pass alone and fail together 2026-10-30 UTC
Meta² teaches AI agents when to change their working setup 2026-11-03 UTC
TACT puts an AI council to work on qualitative data—with humans retaining judgment 2026-11-03 UTC

token efficiency Current 3 Previous 0 Change +3

Current window · 3 articles

Knowing When to Stop Is Still a Challenge for Reasoning AI 2026-10-30 UTC
A Formula-Aware Map Helps AI Navigate Spreadsheets with Less Data 2026-10-30 UTC
Reading the warning signs: an explainable way to stop failing web agents early 2026-11-03 UTC

uncertainty Current 3 Previous 0 Change +3

Current window · 3 articles

Virtual Sensors Seek the Source of Industrial Faults 2026-11-03 UTC
A simulated city tests whether AI investigators can separate evidence from suspicion 2026-11-03 UTC
CoCo turns textual context into numerical guidance for time-series forecasts 2026-11-03 UTC

uncertainty estimation Current 3 Previous 0 Change +3

Current window · 3 articles

LaplaceDiag uses changing actuator effects to narrow equipment fault searches 2026-11-02 UTC
When Less Data Helps: A Task-Focused Approach to Machine Learning 2026-11-02 UTC
When AI learns new facts, its confidence may lag behind 2026-11-03 UTC

verifiable rewards Current 3 Previous 0 Change +3

Current window · 3 articles

A Subgroup-Aware Baseline Offers Modest Gains in AI Math Training 2026-10-31 UTC
Why AI Reasoning Training May Favor Familiar Problems 2026-11-02 UTC
GIST Selects Which Answers—and Which Tokens—to Use in Offline AI Training 2026-11-04 UTC

vllm Current 3 Previous 0 Change +3

Current window · 3 articles

When 4-Bit AI Models Run Faster—and When the Advantage Disappears 2026-11-03 UTC
Hybrid Spark pairs prediction with copying to speed up AI code editing 2026-11-03 UTC
SafeStart targets the safety cost of running fewer AI experts 2026-11-04 UTC

Plant Biology keywords

preprint Current 22 Previous 0 Change +22

Current window · 22 articles

Extra lobes on morning glory leaves point to a more complex genetic story 2026-11-02 UTC
A familiar plant enzyme may help send damaged mitochondria for recycling 2026-11-02 UTC
Waterlily study links pollen rejection to reactive oxygen and two interacting proteins 2026-11-02 UTC
Sugars help rice leaves sustain production of antimicrobial compounds 2026-11-02 UTC
Compost helps tomato plants preserve photosynthetic function under severe drought 2026-11-03 UTC
Fertilizer mix trades some orchid yield for higher compound levels in greenhouse trial 2026-11-03 UTC
Plant cell screen separates fast growth from staying power 2026-11-03 UTC
RNA decay protein helps regulate Arabidopsis’s circadian clock 2026-11-02 UTC
Protein markers reveal early polarity in Arabidopsis reproductive development 2026-11-02 UTC
Nanoparticles reshape photosynthetic plant-cell cultures across repeated treatments 2026-11-03 UTC
Persimmon study traces natural astringency loss to two types of gene damage 2026-11-03 UTC
Avocado fruit stalks add sugar-carrying tubes as fruits develop 2026-11-02 UTC
An RNA-based brake may help Arabidopsis keep putrescine in balance 2026-11-02 UTC
Rice stem study points to a gravity-sensing layer beside its protective barrier 2026-11-02 UTC
Barley root study narrows search for genes linked to growth under salt stress 2026-11-03 UTC
A missing nitrate transporter leaves marine algae starved amid plenty 2026-11-03 UTC
Iron-response regulator helps Arabidopsis roots withstand salt stress 2026-11-04 UTC
Chromatin proteins link a plant clock gene to flowering time in Arabidopsis 2026-11-04 UTC
Shared chemical clues help connect tomato genes to unidentified metabolites 2026-11-03 UTC
Slipper orchids show striking scent diversity, with only weak ties to ancestry 2026-11-04 UTC
Barley grain filling follows a changing pattern of parental gene activity 2026-11-04 UTC
The Missing Silicon in a Diatom’s Glass Workshop 2026-11-05 UTC

arabidopsis thaliana Current 12 Previous 1 Change +11

Current window · 12 articles

A familiar plant enzyme may help send damaged mitochondria for recycling 2026-11-02 UTC
Plant cell screen separates fast growth from staying power 2026-11-03 UTC
A short protein segment helps direct SOSEKI to plant cell edges 2026-11-02 UTC
An RNA quality-control pathway has opposing roles in plant heat recovery 2026-11-02 UTC
Protein markers reveal early polarity in Arabidopsis reproductive development 2026-11-02 UTC
Nanoparticles reshape photosynthetic plant-cell cultures across repeated treatments 2026-11-03 UTC
An RNA-based brake may help Arabidopsis keep putrescine in balance 2026-11-02 UTC
Faster membrane remodeling does not mean faster greening in seedlings 2026-11-04 UTC
A tiny genetic prelude helps Arabidopsis make a key light sensor 2026-11-04 UTC
Iron-response regulator helps Arabidopsis roots withstand salt stress 2026-11-04 UTC
How a chloroplast transporter helps shape the air inside a leaf 2026-11-04 UTC
Chromatin proteins link a plant clock gene to flowering time in Arabidopsis 2026-11-04 UTC

Previous window · 1 articles

Cold reshapes RNA splicing while plant genes are still being copied 2026-10-29 UTC

plant genetics Current 5 Previous 0 Change +5

Current window · 5 articles

Extra lobes on morning glory leaves point to a more complex genetic story 2026-11-02 UTC
Plant lineages diverge in DNA methylation without demethylases 2026-10-30 UTC
A plant genetic switch separates DNA delivery from integration 2026-10-30 UTC
Genetic study identifies candidate markers for Pakistani wheat variety testing 2026-11-03 UTC
Barley grain filling follows a changing pattern of parental gene activity 2026-11-04 UTC

tomato Current 5 Previous 0 Change +5

Current window · 5 articles

A sugar-binding protein helps a tomato pathogen multiply in leaves 2026-10-30 UTC
Tomato gene duplicates often retain ancestral expression patterns 2026-10-30 UTC
Urban biowaste compost reshapes bacteria around tomato roots 2026-10-30 UTC
Compost helps tomato plants preserve photosynthetic function under severe drought 2026-11-03 UTC
Shared chemical clues help connect tomato genes to unidentified metabolites 2026-11-03 UTC

arabidopsis Current 3 Previous 1 Change +2

Current window · 3 articles

Plant lineages diverge in DNA methylation without demethylases 2026-10-30 UTC
A plant genetic switch separates DNA delivery from integration 2026-10-30 UTC
RNA decay protein helps regulate Arabidopsis’s circadian clock 2026-11-02 UTC

Previous window · 1 articles

Fungal Volatiles Linked to Root Growth Under Osmotic Stress 2026-10-29 UTC

auxin Current 3 Previous 2 Change +1

Current window · 3 articles

Extra lobes on morning glory leaves point to a more complex genetic story 2026-11-02 UTC
How maize leaves build bridges between their veins 2026-11-02 UTC
Barley root study narrows search for genes linked to growth under salt stress 2026-11-03 UTC

Previous window · 2 articles

Rice may sense soil pH through changes in iron availability 2026-10-29 UTC
Fungal Volatiles Linked to Root Growth Under Osmotic Stress 2026-10-29 UTC

gene expression Current 3 Previous 0 Change +3

Current window · 3 articles

Tomato gene duplicates often retain ancestral expression patterns 2026-10-30 UTC
Plant lineages diverge in DNA methylation without demethylases 2026-10-30 UTC
Birch gene activity offers clues to contrasting salt-stress responses 2026-11-02 UTC

photosynthesis Current 3 Previous 1 Change +2

Current window · 3 articles

Sugars help rice leaves sustain production of antimicrobial compounds 2026-11-02 UTC
Nanoparticles reshape photosynthetic plant-cell cultures across repeated treatments 2026-11-03 UTC
A missing nitrate transporter leaves marine algae starved amid plenty 2026-11-03 UTC

Previous window · 1 articles

Green algae show varied hydrogen responses when light returns after anoxia 2026-10-29 UTC

plant breeding Current 3 Previous 0 Change +3

Current window · 3 articles

Waterlily study links pollen rejection to reactive oxygen and two interacting proteins 2026-11-02 UTC
Persimmon study traces natural astringency loss to two types of gene damage 2026-11-03 UTC
Cacao DNA offers clues to black pod resistance from a sparse disease screen 2026-11-05 UTC

reactive oxygen species Current 3 Previous 0 Change +3

Current window · 3 articles

C4 leaf cells show distinct chloroplast-to-nucleus signalling 2026-10-30 UTC
Waterlily study links pollen rejection to reactive oxygen and two interacting proteins 2026-11-02 UTC
Iron-response regulator helps Arabidopsis roots withstand salt stress 2026-11-04 UTC

Economics keywords

preprint Current 14 Previous 0 Change +14

Current window · 14 articles

Japan college-access model shows how moving barriers can widen regional gaps 2026-10-31 UTC
Why more firms do not always mean more precise estimates of economic shocks 2026-10-31 UTC
A stable menu of job contracts can exist when no single deal is stable 2026-10-31 UTC
When a Storm Travels Through a Social Network—and Toward Credit Markets 2026-11-01 UTC
Tracking specific parts makes simulated automotive supply shocks four to five times larger 2026-11-01 UTC
When spillovers make ignoring A/B test data the safest static estimate 2026-11-01 UTC
Food Shops and Population Are Linked Across Japan’s Municipal Boundaries 2026-11-02 UTC
How much persuasion survives when information comes in separate parts? 2026-11-02 UTC
Tracking Poland’s Economic Policy Uncertainty Through Newspaper Coverage 2026-11-03 UTC
Digital trade tariffs could raise revenue—but the gains depend on uncertain assumptions 2026-11-03 UTC
Seoul’s cram-school access shows up in housing prices, preprint finds 2026-11-04 UTC
When selling items separately earns the most: a finite-value auction result 2026-11-04 UTC
Glasswing study links frontier AI access to more disclosed software flaws—not fewer observed exploits 2026-11-04 UTC
Risk Aversion Can Break a Standard Bidding Assumption in Multiunit Auctions 2026-11-04 UTC

economic theory Current 12 Previous 0 Change +12

Current window · 12 articles

When research findings are private, simple success bonuses can be optimal 2026-10-31 UTC
Cheaper fact-checking can backfire when recommenders adjust their standards 2026-10-31 UTC
When AI Makes Research Cheaper, Verification Can Become the Bottleneck 2026-11-01 UTC
When cheaper AI-assisted research makes scientific verification harder 2026-11-03 UTC
Why Learning That a Partner Enjoys an Activity Can Bring It to an End 2026-11-01 UTC
When Choosing Risk Can Make Competition for Partners More Efficient 2026-11-02 UTC
Markets, Coercion and the Choices People Make Before Trading 2026-11-02 UTC
How much persuasion survives when information comes in separate parts? 2026-11-02 UTC
When AI Makes Proving Ability More Expensive 2026-11-02 UTC
When indifference between identical bets rules out correlation effects 2026-11-03 UTC
AI’s economic impact may depend on teamwork, not just smarter machines 2026-10-31 UTC
Risk Aversion Can Break a Standard Bidding Assumption in Multiunit Auctions 2026-11-04 UTC

causal inference Current 9 Previous 3 Change +6

Current window · 9 articles

How Medical Cutoffs Can Help Researchers Identify Treatment Effects 2026-11-02 UTC
Tracing Stock-Market Wealth into Local Payrolls, with Clearer Causal Assumptions 2026-11-02 UTC
Projected Instruments Offer a Conditional Route to Estimating Causal Effects 2026-10-31 UTC
When spillovers make ignoring A/B test data the safest static estimate 2026-11-01 UTC
Choosing Causal Comparisons by Looking Forward, Not Just Back 2026-11-01 UTC
When Spillover Tests Shape an Experiment’s Next Question 2026-11-02 UTC
When Statistical Controls Hide the Trends Researchers Need to See 2026-11-02 UTC
When an Information Constraint Rules Out Hidden Confounding 2026-11-02 UTC
Finding policy effects that averages can miss 2026-11-03 UTC

Previous window · 3 articles

Meta-analysis compares traditional and modern difference-in-differences estimates 2026-10-29 UTC
When Different Differences Tell Similar Stories 2026-10-29 UTC
When uncertain policy estimates make caution optimal 2026-10-29 UTC

econometrics Current 8 Previous 2 Change +6

Current window · 8 articles

Selecting predictors one at a time to separate signals from correlated proxies 2026-11-03 UTC
Why more firms do not always mean more precise estimates of economic shocks 2026-10-31 UTC
Testing When Ordinary Regression Can Stand In for a Structural Model 2026-11-01 UTC
When Statistical Controls Hide the Trends Researchers Need to See 2026-11-02 UTC
When Missing Data Make Regression Results Look Too Certain 2026-11-03 UTC
How combining outcomes can change an economic study’s conclusion 2026-11-03 UTC
Finding policy effects that averages can miss 2026-11-03 UTC
When Many AI-Generated Controls Can Help Regression—and When They Cannot 2026-11-04 UTC

Previous window · 2 articles

New Theory for Threshold Regression with Persistent Variables 2026-10-29 UTC
Meta-analysis compares traditional and modern difference-in-differences estimates 2026-10-29 UTC

game theory Current 7 Previous 2 Change +5

Current window · 7 articles

When coalition bargaining has one payoff prediction—and when it has several 2026-10-31 UTC
Why an AI Pause Could Lose Its Deterrent Power Even Without Cheating 2026-11-03 UTC
When More Project Transparency Can Make Team Communication Less Honest 2026-11-03 UTC
A new algorithm tackles equilibrium in the continuous Colonel Blotto game 2026-11-03 UTC
Randomized strategies need at most one extra round of elimination 2026-11-03 UTC
When Random Outcomes Merge, Strategic Equilibrium Can Disappear 2026-11-04 UTC
When limited resources change what makes a network stable 2026-11-04 UTC

Previous window · 2 articles

When network structure makes strategic opposites equivalent 2026-10-29 UTC
How network position shapes strategic communication 2026-10-29 UTC

large language models Current 6 Previous 0 Change +6

Current window · 6 articles

AI-generated survey answers can preserve group patterns while missing individuals 2026-10-30 UTC
Small behavioral profiles improve AI simulations—but the gains depend on the game 2026-10-31 UTC
Lean behavioral profiles improve AI simulations—but not every kind of prediction 2026-10-31 UTC
Same Words, Different Scores: How Authorship Labels Sway AI Judges 2026-11-01 UTC
AI panel ranks parties’ green pledges—but reads them as greener than experts do 2026-11-01 UTC
Can faster AI models capture the economic choices people disagree on? 2026-11-03 UTC

mechanism design Current 6 Previous 1 Change +5

Current window · 6 articles

Identical houses complicate the case for top trading cycles 2026-11-02 UTC
An auction model links seller revenue to who gets to learn 2026-11-03 UTC
When Proving an Honest Claim Costs Money, Bankruptcy Rules Matter 2026-11-03 UTC
Searching for facility-location rules that make honesty worthwhile 2026-11-03 UTC
When a neural network’s memories become a game’s equilibria 2026-11-03 UTC
When selling items separately earns the most: a finite-value auction result 2026-11-04 UTC

Previous window · 1 articles

A local-search approach to recognizing dominant strategies 2026-10-29 UTC

partial identification Current 6 Previous 0 Change +6

Current window · 6 articles

What Incomplete Records Can Reveal About Joint Outcomes 2026-11-02 UTC
What Can Regression Reveal When Key Variables Are Only Known Within Ranges? 2026-11-02 UTC
When Missing Data Make Regression Results Look Too Certain 2026-11-03 UTC
Left-digit bias may hide the welfare cost of sales taxes 2026-11-03 UTC
How Much Can an Economic Study’s Assumptions Fail Before Its Conclusion Changes? 2026-11-03 UTC
What Hidden Bids Let Sellers Learn About Auction Reserves 2026-11-04 UTC

information design Current 4 Previous 0 Change +4

Current window · 4 articles

Cheaper fact-checking can backfire when recommenders adjust their standards 2026-10-31 UTC
How much persuasion survives when information comes in separate parts? 2026-11-02 UTC
When More Project Transparency Can Make Team Communication Less Honest 2026-11-03 UTC
Learning to Persuade When Users Can Game the Learning Process 2026-11-03 UTC

artificial intelligence Current 3 Previous 1 Change +2

Current window · 3 articles

When AI Makes Proving Ability More Expensive 2026-11-02 UTC
AI’s economic impact may depend on teamwork, not just smarter machines 2026-10-31 UTC
AI exposure is not a measure of relief from difficult work 2026-11-04 UTC

Previous window · 1 articles

Survey explores what workers value beyond their pay 2026-10-29 UTC

consumer spending Current 3 Previous 0 Change +3

Current window · 3 articles

How social ties could carry household shocks into credit markets 2026-11-01 UTC
When a Storm Travels Through a Social Network—and Toward Credit Markets 2026-11-01 UTC
Can faster AI models capture the economic choices people disagree on? 2026-11-03 UTC

difference-in-differences Current 3 Previous 2 Change +1

Current window · 3 articles

After floods, carmakers add engine production sites rather than retreat 2026-10-31 UTC
Choosing Causal Comparisons by Looking Forward, Not Just Back 2026-11-01 UTC
When Statistical Controls Hide the Trends Researchers Need to See 2026-11-02 UTC

Previous window · 2 articles

Meta-analysis compares traditional and modern difference-in-differences estimates 2026-10-29 UTC
When Different Differences Tell Similar Stories 2026-10-29 UTC

instrumental variables Current 3 Previous 0 Change +3

Current window · 3 articles

Corporate Debt Persistence Extends Across Product-Market Networks 2026-11-02 UTC
Balancing statistical tests when no single choice is best 2026-11-04 UTC
When Many AI-Generated Controls Can Help Regression—and When They Cannot 2026-11-04 UTC

linear programming Current 3 Previous 0 Change +3

Current window · 3 articles

A Longest-Queue Rule for Matching Markets Where Agents Can Leave 2026-11-01 UTC
An auction model links seller revenue to who gets to learn 2026-11-03 UTC
Searching for facility-location rules that make honesty worthwhile 2026-11-03 UTC

machine learning Current 3 Previous 0 Change +3

Current window · 3 articles

AI-generated survey answers can preserve group patterns while missing individuals 2026-10-30 UTC
Hiring models predict retention locally—but disagree across employers 2026-10-31 UTC
Finding policy effects that averages can miss 2026-11-03 UTC

pareto efficiency Current 3 Previous 0 Change +3

Current window · 3 articles

When Choosing Risk Can Make Competition for Partners More Efficient 2026-11-02 UTC
Markets, Coercion and the Choices People Make Before Trading 2026-11-02 UTC
Identical houses complicate the case for top trading cycles 2026-11-02 UTC

peer review Current 3 Previous 0 Change +3

Current window · 3 articles

Same Words, Different Scores: How Authorship Labels Sway AI Judges 2026-11-01 UTC
When AI Makes Research Cheaper, Verification Can Become the Bottleneck 2026-11-01 UTC
When cheaper AI-assisted research makes scientific verification harder 2026-11-03 UTC

Astrophysics keywords

Insufficient data: no metadata keyword appears on 3 or more current-window records.