Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

📄 arXiv: 2609.09153v1 📥 PDF

作者: Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan Ö. Arık

分类: cs.AI, cs.CL, cs.MA

发布日期: 2026-09-08

备注: 36 pages including references and appendices, 6 figures, 11 tables


💡 一句话要点

提出程序图以解决长时间规划中的行动选择问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 大型语言模型 程序图 自我演化 决策优化 任务规划 智能代理 动态调整

📋 核心要点

  1. 现有的代理方法在长时间规划中容易失去目标,导致行动选择不当和重复无效操作。
  2. 论文提出程序图,通过将程序知识结构化为三元组,提供明确的行动指导,并实现自我演化以优化决策过程。
  3. 实验结果表明,程序图在多个数据集和任务上均优于传统的基于记忆的方法,且自我演化进一步提升了性能。

📝 摘要(中文)

随着大型语言模型(LLM)作为代理被广泛应用于长期规划和外部工具的操作,现有方法在选择行动时往往依赖于不受限制的生成,导致程序知识隐含。随着轨迹的延长,代理可能会失去目标,错误调用工具,重复无效行动。本文提出程序图,将程序知识组织为(过程,关系,过程)三元组,提供明确的行动指导。该框架通过自我演化机制,利用成功与失败的轨迹对比,动态调整图的拓扑结构,显著提升了多个数据集和任务类型上的性能,超越了基于记忆的基线方法。

🔬 方法详解

问题定义:本文旨在解决大型语言模型在长期规划中行动选择不当的问题,现有方法往往缺乏明确的程序知识,导致目标模糊和无效重复。

核心思路:提出程序图,将程序知识以(过程,关系,过程)三元组的形式组织,提供清晰的行动指导,并通过自我演化机制优化图的结构。

技术框架:整体架构包括程序图的构建、决策步骤中的节点定位、以及指导模型的生成。程序图在每个决策步骤中提供上下文信息,指导代理的下一步行动。

关键创新:程序图的自我演化机制是其核心创新,通过对比成功与失败的轨迹,动态调整图的拓扑结构,显著提高了决策的有效性。

关键设计:在设计中,程序图从一个最小的骨架开始构建,采用特定的损失函数来优化图的结构,同时保留被拒绝的编辑以避免重复行为。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,程序图在多个数据集和任务类型上均超越了基于记忆的基线方法,性能提升幅度显著。自我演化机制进一步增强了模型的适应性和决策能力,验证了其在实际应用中的有效性。

🎯 应用场景

该研究的潜在应用领域包括智能助手、自动化决策系统和复杂任务规划等。通过提供明确的行动指导和自我优化能力,程序图能够在多种场景中提升代理的决策效率和准确性,具有广泛的实际价值和未来影响。

📄 摘要(原文)

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions through unconstrained generation over an accumulating history, leaving implicit the procedural knowledge of what to do, in what order, and under which conditions. As trajectories lengthen, agents can lose track of their objectives, invoke tools out of order, and repeat unproductive actions. We introduce the Procedural Graph: just as a knowledge graph organizes factual knowledge into (entity, relation, entity) triplets for what-is questions, a Procedural Graph organizes procedural knowledge into (procedure, relation, procedure) triplets for what-to-do questions. At each decision step, the framework localizes the agent's active node, and a guidance model translates the surrounding subgraph into step-level situational guidance that biases the solver's next action without dictating it. The graph is self-evolving: an LLM refiner contrasts failed trajectories with successful ones and edits the graph's topology and attributes, committing edits that preserve or improve held-out validation performance while retaining rejected ones to discourage repetition. Starting from a minimal skeleton, the loop builds graphs that match or surpass hand-designed ones. It can also repair a flawed expert prior. Across multiple datasets, task types, and LLMs, the Procedural Graph delivers consistent gains over memory-based baselines, and self-evolution further improves performance without manual engineering.