It is found that model scale, reasoning, and agent scaffolding affect abstention in different ways, where larger or more capable models sometimes perform better at timely abstention than larger or more capable models sometimes perform worse at timely abstention.
Hang Luo, Bing-Bing Wen, Lucy Lu Wang· arXiv.org· 19 citations
Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap as the problem of agentic abstention, and existing approaches typically optimize...
Hang Luo, Bing-Bing Wen, Guang Yang et al.· 1 citation
It is established that principled and informed team selection is critical and strong model selection algorithms for assembling effective multi-LLM systems are presented.
Zong-Wan Cao, Zi-Yuan Yang, Shang-Bin Feng et al.· 0 citations
STOP (Structured On-policy Pruning), an on-policy algorithm for analyzing and pruning long-form reasoning traces, which improves the structural efficiency of generated reasoning, and reallocates reasoning effort away from redundant verification and backtracking toward more productive exploration.
Chenjun Xu, Zhen-Nan Zhou, Zhan Su et al.· arXiv.org· 0 citations
A dense, decision-level reward is introduced in which an LLM judge evaluates the necessity of each tool call, which effectively suppresses cue-driven tool use while preserving task performance, providing a practical approach to improving the robustness of LLM agent tool-use policies.
Yi-Wei Yang, Haoxiang Zhang, Bing-Bing Wen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.