CHANNEL ARCHIVE // [166] ARTICLES // PAGE 4 OF 12
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
CHANNEL // 01 [166]
Artificial Intelligence
Research into artificial intelligence and intelligent systems.
DualWorldBench tests whether AI agents can turn delivery goals into workable plans
Source published
- DualWorldBench
- AI agents
- pickup–delivery planning
More platforms do not guarantee better AI recommendations
Source published
- agentic recommendation
- platform competition
- credibility assessment
Coordinated AI agents improve vulnerability exploitation in controlled benchmarks
Source published
- DoGNAVY-Exploit
- open-weight models
- multi-agent systems
Could internal rhythms give AI a different way to process time?
Source published
- sequence-processing AI
- endogenous temporal structure
- neural oscillations
EvoML checks machine-learning pipelines in stages and retains successful repairs
Source published
- EvoML
- automated machine learning
- multi-agent systems
More AI Records, Harder Comparisons: How Federal Inventories Rewrite Accountability
Source published
- AI governance
- US Federal AI Use Case Inventory
- algorithmic accountability
Reading the warning signs: an explainable way to stop failing web agents early
Source published
- web navigation agents
- early termination
- sequential pattern mining
GlucoAgent tests a case-by-case approach to glucose forecasting
Source published
- glucose forecasting
- GlucoAgent
- continuous glucose monitoring
How Worse Model Variants Can Still Guide Better AI Training
Source published
- evolution strategies
- large language models
- derivative-free optimization
Structured Clinical Memory Shows Modest Gains in a Synthetic AI Decision Benchmark
Source published
- structured clinical memory
- probabilistic decision models
- synthetic clinical benchmark
A shared task board for AI agents that need to wait
Source published
- AI agents
- Agent Board
- multi-agent coordination
AlgoPilot teaches language models to choose a solving strategy before answering
Source published
- AlgoPilot
- large language models
- strategy selection
Why AI Reasoning Training May Favor Familiar Problems
Source published
- reinforcement learning
- verifiable rewards
- RLVR
Choosing Less-Repetitive Training Data Could Make AI Fine-Tuning More Efficient
Source published
- instruction tuning
- data selection
- QSGS
LEAP predicts which training hardware offers better value before jobs launch
Source published
- LEAP
- AI training
- throughput prediction