MIND-Skill: 通过多智能体归纳与演绎保证技能质量
MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction
AI总结：
本文提出MIND-Skill框架，通过归纳与演绎自动生成可复用的技能，结合三种损失函数保证质量，实验显示其在AppWorld和BFCL-v3上优于现有方法。
摘要：
大型语言模型（LLM）驱动的AI代理已成为自主解决问题的有希望范式，但它们仍难以处理复杂多步骤现实任务，这些任务需要领域特定的程序知识。可重用的代理技能，封装了成功的解决问题策略，为代理提供基于先前经验的自然解决方案。然而，整理此类技能仍主要依赖人工，需要人类专家将丰富的领域知识提炼成可操作的指南。在本文中，我们提出了MIND-Skill，即多智能体归纳与演绎技能生成框架，该框架能从成功的轨迹中自动归纳出可推广的技能，并通过归纳代理抽象出可重用的技能，以及演绎代理通过遵循归纳出的技能重建轨迹。为了保证生成技能的质量，我们引入了重建损失，比较输入和重建轨迹；结果损失强制执行重建轨迹的正确性；以及评估损失，根据预定义标准评估文档质量和规范抽象级别。这些文本损失与TextGrad联合优化，生成的技能在未见过的任务上进行评估。在AppWorld和BFCL-v3上的实验表明，MIND-Skill在性能上优于现有技能生成方法。
英文摘要：
Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world tasks that demand domain-specific procedural knowledge. Reusable agent skills, which encapsulate successful problem-solving strategies, offer a natural remedy by enabling agents to build on prior experience. However, curating such skills has largely remained a manual endeavor, requiring human experts to distill rich domain knowledge into actionable guidelines. In this work, we present $\textbf{M}$ulti-agent $\textbf{IN}$duction and $\textbf{D}$eduction for $\textbf{Skill}$s ($\textbf{MIND-Skill}$), a framework that automatically induces generalizable skills from successful trajectories with robust quality guarantees. MIND-Skill consists of an induction agent which is tasked to abstract reusable skills from successful trajectories, and a deduction agent which aims to reconstruct trajectories by following the induced skills. To guarantee the quality of the generated skills, we introduce a reconstruction loss that compares input and reconstructed trajectories, an outcome loss that enforces the correctness of the reconstructed trajectories, and a rubric loss that assesses the documentation quality and regularizes the abstraction level of the generated skills according to predefined criteria. These textual losses are jointly optimized with TextGrad, and the resulting skills are evaluated on held-out tasks unseen during optimization. Experiments on AppWorld and BFCL-v3 show that MIND-Skill consistently outperforms concurrent skill generation methods.
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。
