Back to Home
arXiv AI··Papers & Tech

Plan-and-Patch: Diffusion Language Models for Agentic Planning

中文摘要

Plan-and-Patch模型利用扩散语言模型进行智能体规划,通过局部修订机制有效应对环境变化和执行错误,提升长序列任务的执行成功率与协作能力。

English Summary

Plan-and-Patch uses diffusion language models to enable agents to dynamically revise long-horizon plans, addressing environment uncertainties and execution failures through targeted, efficient mid-process corrections.

Original Excerpt

arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agents must therefore not only generate plans, but also revise them. Such revisions often affect only part of a plan, leaving the preceding and subsequent structure intact. Rather than regenerate the entire plan and risk unnecessary changes, repair can regenerate the affected region conditioned on the preserved prefix and suffix. We introduce Plan-and-Patch, a plan-and-act framework in which a diffusion language model (dLLM) generates a structured, program-like plan through parallel unmasking and repairs it by filling in selected regions while keeping the surrounding steps fixed. We compare DreamReasoner-8B and Qwen3-8B as diffusion and autoregressive (AR) planners. On Natural Plan without task-specific training, diffusion (53.7%) achieves nearly twice the plan repair success rate of AR (27.0%). After task-specific training …