让网页智能体能自我纠错，关键在每步计划都可被验证真假。
Falsifiable Commitment Planning for Self-Correcting Web Agents
- 每一步计划都带可验证的证据和反例，支持动态信任判断。
- 在WebArena上成功率比最强基线提升13.8%，长任务表现更优。
- 适合需要长时间、高可靠性自动操作的网页任务场景。
长期任务的网页智能体常在最终失败前偏离目标：轨迹虽局部合理，但当前状态、技能或计划假设已不再支持用户指令。现有智能体虽能规划、反思或复用经验，却极少明确说明哪些证据支持继续执行某一步。本文提出FCPAgent，一种可验证承诺的规划框架，用于构建鲁棒的长期网页智能体。每个计划步骤被表示为可验证承诺单元（FCU）：包含可复用技能、确认证据、反例证据及置信度。执行采用计划-测试-修复循环。混合承诺检测模块在动作执行前后检查候选行为与观测结果；为提升效率，结合轻量级证据匹配与大模型诊断验证。当证据否定承诺时，范围感知修复机制将矛盾定位到执行、技能或规划层级，并仅修正最小必要部分。在WebArena上，FCPAgent相比最强基线平均成功率提升13.8%，尤其在长周期任务中表现显著。
原文摘要 · Abstract (English)
Long-horizon web agents often go off track before final failure: a trajectory can remain locally plausible even after the current state, reused skill, or plan assumption no longer supports the user instruction. Existing agents can plan, reflect, or reuse experience, but their plans rarely specify the evidence under which an active step should still be trusted. We propose FCPAgent, a falsifiable commitment planning framework for robust long-horizon web agents. FCPAgent represents each plan step as a Falsifiable Commitment Unit (FCU): a subgoal grounded in a reusable skill, together with confirming evidence, falsifying evidence, and a confidence score. Execution is organized as a plan-test-repair loop. The hybrid commitment testing module checks candidate actions before they modify the browser and checks observations after execution; for efficiency, it combines lightweight evidence matching with LLM-based diagnostic verification. When evidence falsifies a commitment, scope-aware repair localizes the contradiction to the execution, skill, or planning level and revises the smallest adequate part. On WebArena, FCPAgent achieves a 13.8% relative improvement in average success over the strongest baseline, with especially large gains on long-horizon tasks.
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。