自动化 Thought of Search：迈向可靠性与完备性的旅程
Automating Thought of Search: A Journey Towards Soundness and Completeness
AI总结：
本文提出 AutoToS，通过通用与领域特定单元测试的反馈引导语言模型自动生成可靠且完备的搜索组件，移除了人在回路的需求，在所有评估领域均以少量 LLM 调用实现 100% 准确率。
摘要：
大型语言模型（LLMs）正被用于解决需要搜索的规划问题。大多数文献将 LLMs 用作世界模型来定义搜索空间，为了灵活性而放弃了可靠性。最近的一项工作 Thought of Search（ToS）提出用代码定义搜索空间，由 LLMs 生成该代码。ToS 需要人在回路中，协作生成可靠的后续函数和目标测试。然而，其结果是值得付出努力的：所有测试的数据集均以 100% 的准确率求解。因此，自动化 ToS 过程具有巨大潜力。我们朝着自动化 ToS（AutoToS）迈出了重要的第一步，将人从与语言模型交互的回路中移除。AutoToS 通过来自通用和特定领域单元测试的反馈，逐步引导语言模型生成可靠且完备的搜索组件。我们表明，AutoToS 能够在所有评估领域以少量 LLM 调用实现 100% 的准确率。
英文摘要：
Large language models (LLMs) are being used to solve planning problems that require search. Most of the literature uses LLMs as world models to define the search space, forgoing soundness for the sake of flexibility. A recent work, Thought of Search (ToS), proposed defining the search space with code, having LLMs produce that code. ToS requires a human in the loop, collaboratively producing a sound successor function and goal test. The result, however, is worth the effort: all the tested datasets were solved with 100% accuracy. Consequently, there is great potential to automate the ToS process. We take a first major step towards automating ToS (AutoToS), taking the human out of the loop of interactions with the language model. AutoToS guides the language model step by step towards the generation of sound and complete search components, through feedback from both generic and domain specific unit tests. We show that AutoToS is able to achieve 100% accuracy on all the evaluated domains with a small number of LLM calls.
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。
