超越单次检索：通过查询规划实现多步工具检索
Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning
AI总结：
本文提出TOOLQP框架，通过迭代查询规划解决多步工具检索问题，实现更高效的检索和执行能力。
摘要：
大型语言模型代理在处理大量动态工具库时依赖有效的检索，但标准的单次密集检索器在处理复杂请求时表现不佳。这些失败主要源于抽象用户目标与技术文档之间的脱节，以及固定大小嵌入向量对组合工具组成的有限建模能力。为了解决这些挑战，我们提出了TOOLQP，一个轻量级框架，将检索建模为迭代查询规划。与单次匹配不同，TOOLQP将指令分解为子任务，并动态生成查询以与检索器交互，通过针对组合所需的特定子任务有效弥合语义鸿沟。我们通过合成查询轨迹进行训练，随后通过可验证奖励的强化学习（RLVR）进行优化。实验表明，TOOLQP实现了最先进的性能，表现出优越的零样本泛化能力、在不同检索器上的鲁棒性以及在下游代理执行中的显著改进。
英文摘要：
LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose TOOLQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, TOOLQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train TOOLQP using synthetic query trajectories followed by optimization via Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that TOOLQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.
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。
