arXiv cs.CL· Tanish Kher, Sarvesh DK, Abedelkadir Asi, Sparsha Chennarayapatna Sundaresh, Dezhi Hong·· 2 天前AI 评分32
TRACER：面向 LLM 智能体的轨迹感知工具检索
TRACER: Trajectory-Aware Tool Retrieval for LLM Agents
AI 导读
TRACER 是一种面向 LLM 智能体的工具检索前端，用 trie 索引已观测到的工具调用序列，并通过学习到的经验先验与上下文先验混合排序后续调用。在零售与电信混合的 τ² 环境中，它让 GPT-5.4 的工具选择准确率提升 4.7 个百分点，每步输入 token 减少 80%，仅暴露 128 个工具中的 5 个。
正文 · 原文
Abstract:Modern agents select tools from registries, but exposing entire registries incurs high token costs and can impair selection as they grow. We present TRACER, a retrieval front-end that indexes observed tool-call sequences in a trie and ranks continuations using a learned blend of empirical and contextual priors. On a mixed retail-and-telecom $\tau^2$ environment, TRACER improves GPT-5.4's tool-selection accuracy by 4.7 points while reducing input tokens per step by 80%, exposing just 5 of 128 tools. In autonomous full-turn execution, it matches GPT-5.4's full-registry task success with 61% fewer input tokens per step. Across six environments and four models, TRACER improves tool-selection accuracy over full-registry selection in 21 of 24 model-environment pairs, with average gains of 6 to 10 points; the three exceptions trail by at most 2.2. We analyze failures in both regimes to identify directions for future work.
| Comments: | 21 pages, 7 figures, 23 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| ACM classes: | I.2.7; I.2.6; H.3.3 |
| Cite as: | arXiv:2610.21267 [cs.CL] |
| (or arXiv:2610.21267v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21267 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tanish Kher [view email]
[v1]
Thu, 15 Oct 2026 05:00:58 UTC (67 KB)
来源：arXiv cs.CL · arxiv.org