2 papers
cs.CL2026
EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
Yuyao Wang, Zhongjian Zhang, Mo Chi +7
Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to stor…
cs.LG2026
Finite-Time Regret Analysis of Retry-Aware Bandits
Bingkui Tong, Junpei Komiyama, Soichiro Nishimori +1
We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@ and max@. Given a posterior over…