发表机构
Ant International（蚂蚁国际）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出诊断引导的修复框架DARC，通过先诊断故障类型再进行选择性自修正，在ALFWorld等三个任务场景中提升了智能体平均任务性能并减少资源消耗，为缺乏类编译器反馈的领域构建可靠智能体提供了实用路径。
AI 中文摘要
自修正尤为有用，当故障会限制后续修复时。编码智能体得益于这一特性，因为编译器、测试用例和执行轨迹可将诸多故障转化为类型化的修复信号，但通用语言智能体任务往往仅暴露粗粒度的任务故障。这给通用修复策略带来了矛盾：它们在系统需要更窄的修复接口时，反而扩大了智能体的上下文，将无效动作、缺失过程和严格格式错误等不兼容信号混合。我们的洞见是，开发集故障可通过在测试时修正前确定哪些修复干预是可接受的，来恢复部分缺失的诊断基础。我们提出DARC，一种诊断引导的修复框架，该框架对任务族故障模式进行分析，从共享修复库中修剪不匹配的干预措施，并冻结验证器选定的成功-代价策略用于部署。这种因果顺序使修正具有选择性：框架首先确定何种故障可被修复，然后决定投入多少修复证据。在ALFWorld、AppWorld和XBRL Finance中，相同的协议分别产生了动作有效性框架、过程性修复后备和格式精度检索策略；在每个评估场景中，它都比基础智能体和通用策略提高了平均任务性能，同时减少了环境步骤或检索预算。我们的实验表明，故障无需触发均匀更多的上下文：DARC将自修正从提示扩展转化为修复接口设计。DARC为缺乏类编译器反馈的领域提供了一条构建更可靠智能体的实用路径：在扩大上下文前使故障可执行。
英文摘要
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure. This creates a tension for generic recovery playbooks: they broaden the agent's context precisely when the system needs a narrower repair interface, mixing incompatible signals for invalid actions, missing procedures, and strict-format errors. Our insight is that development-set failures can recover part of the missing diagnostic substrate by deciding which recovery interventions are admissible before test-time correction. We propose DARC, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment. This causal order makes correction selective: the harness first determines what kind of failure can be repaired, then decides how much recovery evidence to spend. In ALFWorld, AppWorld, and XBRL Finance, the same protocol yields an action-validity harness, a procedural-recovery fallback, and a format-precision retrieval policy; in each evaluated setting it improves average task performance over base agents and broad playbooks while reducing environment steps or retrieval budget. Our experiments show that failures need not trigger uniformly more context: DARC turns self-correction from prompt expansion into recovery-interface design. DARC provides a practical route toward more reliable agents in domains where compiler-like feedback is absent: making failures actionable before making contexts larger.
