研究人员开发了一种称为“随机比特超额”（Bits-over-Random, BoR）的随机校正指标，用于评估 LLM 代理在给定查询时应考虑的最佳工具数量。该指标有助于确定在特定工具短名单深度下的成功是否优于随机选择。通过强化学习应用此原理，代理学会了根据查询调整其工具短名单的大小，显著减少了呈现的工具数量，同时保持或提高了覆盖率和 LLM 选择的准确性。 AI
影响 通过减少不必要的工具考虑来优化 LLM 代理的效率，可能提高响应时间和准确性。
排序理由 关于 LLM 代理新指标和评估方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.24660v1 Announce Type: cross Abstract: Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model struggles to choose. Show too few and the correct …
Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model struggles to choose. Show too few and the correct tool may not appear. Most systems apply a fixed sh…