让大模型长时任务执行可回溯，出错后能恢复重来。
AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
- 记录上下文与环境状态快照，支持运行时回退
- 在工程任务中提升成功率和进度完成度
- 适合需要长期规划的复杂自动化场景
许多真实世界任务要求大模型代理在长时间范围内与环境交互。早期出现的错误可能在代理上下文和环境状态中持续传播，后续动作难以纠正。现有方法主要通过计划优化和安全检查减少错误，但对已发生错误缺乏应对能力。为此，我们提出AgentRewind，一个运行时恢复框架，通过记录对齐的代理上下文与受控环境快照，使代理能够回退到先前状态，并携带之前尝试的信息继续执行。我们还构建了MettleBench，一个用于评估长时程工程任务中任务完成度与部分进展的基准测试集，包含一系列相关需求。在多种任务、模型、执行策略和代理架构上的实验表明，AgentRewind相比基线方法显著提升了任务成功率与平均检查清单进度。
原文摘要 · Abstract (English)
Many real-world tasks require LLM agents to interact with their environments over long execution horizons. Errors that occur early in execution may propagate through both the agent context and environment state, and their effects may be difficult to reverse through subsequent actions. Existing methods mainly seek to reduce such errors through plan refinement and safety checks but provide little support after errors occur. To enable recovery during long-horizon execution, we present AgentRewind, a runtime recovery framework that records aligned checkpoints of the agent context and controlled environment, allowing agents to return to an earlier state and resume execution with information from previous attempts. We also construct MettleBench, a benchmark for evaluating task completion and partial progress on long-horizon engineering assignments containing a series of related requirements. Experiments across tasks, multiple models, execution strategies, and agent harnesses show that AgentRewind improves task success rate and average checklist progress over the compared baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。