GRETEL：面向大语言模型工具选择增强的目标驱动、基于检索与执行的试验框架
GRETEL: A Goal-driven Retrieval and Execution-based Trial Framework for LLM Tool Selection Enhancing
AI总结：
针对语义检索难以判断工具实际可用性的问题，本文提出 GRETEL，通过沙箱化规划-执行-评估循环验证候选工具，并在 ToolBench 上显著提升工具选择指标。
摘要：
尽管大语言模型能力取得了显著进展，基于智能体的系统中的工具检索仍从根本上受制于对语义相似性的依赖，而语义相似性无法捕捉功能可行性。现有方法常因参数不匹配、认证失败和执行约束，检索到文本相关但功能上不可用的工具——我们将这一现象称为语义-功能鸿沟。我们提出 GRETEL，通过系统化的实证验证来弥合该鸿沟。GRETEL 实现了一种智能体工作流，对语义检索得到的候选工具执行沙箱化的“规划-执行-评估”循环，生成以执行为依据的证据，以区分真正可用的工具与仅在描述上匹配的工具。我们在 ToolBench 基准上的综合评估表明，所有指标均有显著提升：Pass Rate@10 从 0.690 升至 0.826，Recall@10 从 0.841 改善至 0.867，NDCG@10 从 0.807 上升至 0.857。这些结果证明，相比仅依赖语义相似性，基于执行的验证为工具选择提供了更可靠的基础，可在真实应用中实现更稳健的智能体性能。
英文摘要：
Despite remarkable advances in Large Language Model capabilities, tool retrieval for agent-based systems remains fundamentally limited by reliance on semantic similarity, which fails to capture functional viability. Current methods often retrieve textually relevant but functionally inoperative tools due to parameter mismatches, authentication failures, and execution constraints--a phenomenon we term the semantic-functional gap. We introduce GRETEL, to address this gap through systematic empirical validation. GRETEL implements an agentic workflow that processes semantically retrieved candidates through sandboxed plan-execute-evaluate cycles, generating execution-grounded evidence to distinguish truly functional tools from merely descriptive matches. Our comprehensive evaluation on the ToolBench benchmark demonstrates substantial improvements across all metrics: Pass Rate (at 10) increases from 0.690 to 0.826, Recall (at 10) improves from 0.841 to 0.867, and NDCG (at 10) rises from 0.807 to 0.857.. These results establish that execution-based validation provides a more reliable foundation for tool selection than semantic similarity alone, enabling more robust agent performance in real-world applications.
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。
