跳到正文
arXiv cs.AI· Yoonho Choi, Taehyeon Han, Seonghyeon Lee·· 4 小时前AI 评分31

JET:面向仓库级问答高效工具调用智能体的“恰到好处探索”微调方法

JET: Just-Enough Exploration Tuning for Efficient Tool-Calling Agents in Repository-Level Question Answering

AI 导读

针对 LLM 智能体在仓库级问答中信息已足够仍继续调用工具的“过度探索”问题,研究者提出微调方法 JET,在信息足够的步骤截断训练轨迹并插入解释性 rationale、对其施加更高损失权重。

正文 · 原文

View PDF HTML (experimental)

Abstract:In repository-level question answering (QA), an agent explores a code repository with tools and should answer a question once enough information is gathered. Nevertheless, we find that LLM agents often continue to invoke tools even after the gathered information is already sufficient to answer. We call this phenomenon over-exploration. Moreover, even though existing methods improve task performance through supervised fine-tuning (SFT) on expert trajectories, SFT also propagates the over-exploration in the trajectories to the agent. To mitigate over-exploration, we propose Just-Enough Exploration Tuning (JET), a fine-tuning method that trains the agent to answer once the gathered information is sufficient. JET truncates each training trajectory at the step where the gathered information becomes sufficient, inserts a rationale that explains why the agent can answer at that step, and fine-tunes the agent with a higher loss weight on the rationale. Experiments on two repository-level QA benchmarks with two open-weight 8B models demonstrate that JET reduces tool calls by 11 to 33% on self-generated trajectories while largely preserving the score. On expert trajectories, JET makes 18 to 28% fewer tool calls than SFT while retaining most of the score gain of SFT. In both cases, JET also lowers the inference cost.
Comments: Preprint. 13 pages, 8 figures, 5 tables
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.22539 [cs.CL]
  (or arXiv:2611.22539v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.22539

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yoonho Choi [view email]
[v1] Tue, 17 Nov 2026 10:30:14 UTC (463 KB)

来源:arXiv cs.AI · arxiv.org