Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 5 days ago • 343
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published Sep 1 • 517
EM^2Mem: Event-Centric Multimodal Memory for Large Language Models Paper • 2609.00551 • Published Sep 1 • 13
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents Paper • 2608.31076 • Published Aug 31 • 22
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use Paper • 2608.20202 • Published Aug 20 • 35
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence Paper • 2608.12036 • Published Aug 12 • 90
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents Paper • 2608.05013 • Published Aug 4 • 40
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories Paper • 2606.13578 • Published Jun 11 • 63
SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories Paper • 2606.01311 • Published May 31 • 33
LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis Paper • 2605.30434 • Published May 28 • 19