arXiv:2608. 08282v1 Announce Type: new Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions.
By Ibne Farabi Shihab, Md Najmus Swaqeeb, Abu Sa-Adat Mohamed Moon-Im Al Ahsan
arXiv:2608. 03219v1 Announce Type: new Abstract: Benchmark gains are often treated as evidence of greater LLM capability.
By Yanchao Li, Wanhao Liu, Jiaqing Xie, Ben Gao, Yanbo Wang, Tianfan Fu, Yuqiang Li
The paper introduces EvoResearcher, a training‑free, inference‑time protocol that enables a frozen large language model to perform cost‑bounded self‑reflection and early stopping. By iterating through generate → self‑critique → revise steps until a maximum depth or a CONFIRMED sentinel is reached, the model can self‑verify its answers within a strict compute budget. The protocol incorporates four self‑reflective meta‑reward components—correctness, efficiency, reflection depth, and tool‑call diversity—implemented as prompt‑level mechanisms, and is validated on Big‑Bench Hard, GSM8K, and MATH benchmarks, achieving comparable accuracy while terminating 82‑88% of items early with only about 2.1 generations per question.
By Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li