发表机构
Apodex（Apodex）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出智能体错误数据集（AED），含50,228对错误诊断数据，并设计五阶段AET流程，通过错误诊断与修正显著提升验证器通过率及模型微调一致性。
AI 中文摘要
一次不成功的LLM智能体运行所包含的信息远多于其最终奖励：智能体可获得的观测、它选择的动作以及环境的响应。要复用这些经验进行学习，需要识别出需要修正的决策，并测试一个具体的替代方案。我们引入了智能体错误数据集（AED），该数据集包含来自33个环境、19个工具框架族和23个策略模型（均为文本型智能体系统）中9,961个源任务的50,228对错误诊断数据。我们保留了源轨迹和执行元数据，以支持跨设置的失败分析和重新诊断，而无需重复原始运行。我们的五阶段智能体错误到训练（AET）流程收集自然失败，生成诊断和提议修正，并对照记录的证据进行核查。在支持重放的情况下，我们在匹配的执行设置下，将修正与来自同一检查点的原始动作重试进行比较。然后，我们为诊断和演员恢复构建独立的训练视图。在3,062对匹配的重放对中，首次提议的修正将验证器通过率从18.4%提升至51.1%，提升了32.7个百分点。使用单独冻结的诊断发布，在1,656个源任务上进行全诊断微调，将Qwen3-8B与内部教师标签的精确步骤一致性（在943例保留集上，三个种子的平均值）从47.2%提升至63.6%。该比较中最强的提示参考得分54.7%，并且在四个递增的训练集规模下，平均一致性均有所提升。在单种子比较的演员训练方案中，仅动作修复训练在WebShop-lite上比仅成功训练高出6.67个百分点。
英文摘要
An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's responses. Reusing this experience for learning requires identifying a decision to revise and testing a concrete alternative. We introduce the Agent Error Dataset (AED), comprising 50,228 error-diagnosis pairs from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text-based agent systems. We retain source traces and execution metadata to support cross-setting failure analysis and re-diagnosis without repeating the original rollout. Our five-stage Agentic Error-to-Training (AET) pipeline collects natural failures, generates diagnoses and proposed corrections, and checks them against recorded evidence. Where replay is supported, we compare corrections with original-action retries from the same checkpoint under matched execution settings. We then construct separate training views for diagnosis and actor recovery. Across 3,062 matched replay pairs, first-proposal corrections raise verifier pass rates from 18.4% to 51.1%, a gain of 32.7 percentage points. Using a separately frozen diagnosis release, full-diagnosis fine-tuning on 1,656 source tasks raises Qwen3-8B's exact-step agreement with internal teacher labels from 47.2% to 63.6%, averaged over three seeds on a 943-case holdout. The strongest prompted reference in this comparison scores 54.7%, and mean agreement improves at each of four increasing training-set sizes. In a single-seed comparison of actor-training recipes, action-only repair training scores 6.67 percentage points higher on WebShop-lite than success-only training.
