Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
Yinghao Chen, Zixi Chen, Bingxiang He +7
Humans need to study only a handful of well-written textbooks to master a discipline and attempt its hardest problems. We argue that an ideal self-evolution method should share the…
cs.AI2026
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Yuhao Zhan, Bingxiang He, Zecong Tang +1
Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery afte…
cs.AI2026
Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
Yuhao Zhan, Tianyu Fan, Linxuan Huang +2
Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation, obscuring intermediate hal…