尝试、检查并重试:一种提升LLMs长上下文工具调用性能的分而治之框架
Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
AI总结:
本文提出Tool-DC框架,通过'尝试-检查-重试'范式提升LLMs在长上下文工具调用任务中的性能,实验表明其在多个基准测试中均优于基线方法。
摘要:
工具调用使大型语言模型(LLMs)能够与外部环境互动。然而,当前方法在处理长上下文工具调用任务中的大量且嘈杂的候选工具时往往力不从心,限制了其在现实中的应用。为此,我们提出了Tool-DC,一种提升LLMs工具调用性能的分而治之框架。Tool-DC的核心是通过“尝试-检查-重试”范式来降低推理难度并充分利用LLMs的自我反思能力。具体而言,Tool-DC包含两个变种:1)无需训练的Tool-DC(TF),其具有即插即用和灵活的特点;2)基于训练的Tool-DC(TB),其更高效。大量实验表明,两种Tool-DC方法均在各方面优于其对应方法。Tool-DC(TF)在BFCL和ACEBench基准上比基线提高了高达+25.10%的平均收益,而Tool-DC(TB)使Qwen2.5-7B能够达到与专有LLMs(如OpenAI o3和Claude-Haiku-4.5)相当或甚至更好的性能。
英文摘要:
Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and noisy candidate tools in long-context tool-calling tasks, limiting their real-world application. To this end, we propose Tool-DC, a Divide-and-Conquer framework for boosting tool-calling performance of LLMs. The core of Tool-DC is to reduce the reasoning difficulty and make full use of self-reflection ability of LLMs via a "Try-Check-Retry" paradigm. Specifically, Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient. Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin. Tool-DC (TF) brings up to +25.10% average gains against the baseline on BFCL and ACEBench benchmarks, while Tool-DC (TB) enables Qwen2.5-7B to achieve comparable or even better performance than proprietary LLMs, e.g., OpenAI o3 and Claude-Haiku-4.5.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。