让大模型只看必要工具，减少误选和浪费。
ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
- 用因果充分性筛选最小必要工具集
- 每步仅暴露1个工具，节省90%令牌开销
- 适合追求高效可靠的智能代理开发者
大型语言模型代理越来越多地依赖外部工具，但工具列表越大，越容易引发错误调用、过早执行和高令牌消耗。现有工具选择方法通常基于语义相关性，暴露名称或描述匹配用户请求的工具。我们认为相关性不足：一个工具可能与任务相关，但在当前步骤仍不必要或过早。我们提出无需训练的因果最小工具过滤（CMTF），通过轻量级前提-效果契约，仅暴露从当前状态推进到目标所需的最小下一步工具集合。在包含102个任务、100个工具、4个LLM后端和2448次运行的主基准测试中，CMTF在整体成功率上达到最强因果基线水平，将可见工具数从100个降至每步1个，并相比全工具暴露减少约90%的令牌使用量。
原文摘要 · Abstract (English)
Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step. We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。