正在加载页面…
本次复现积分预估
预计消耗
549
最大预留
1683
预计算力时长
约 210 分钟
实际消耗 0 积分，扣除 0 积分；算力运行约 0 分钟，模型 Token 0。
另观测到失败尝试使用算力约 14 分钟、模型 Token 7142207；该部分未产出可导入结果，不计入积分。
The paper introduces DoCtOR, a reflection framework for large-language-model multi-agent systems. DoCtOR uses a process-reward-based ProFA diagnosis module to identify the first incorrect reasoning step and responsible agent in a failed trajectory, a counterfactual correction module to propose and score an alternative action, and a reflector that gives targeted feedback to the decisive error agent. The authors evaluate the framework on HotPotQA, ChartQAPro, and Mind2Web, compare it with Reflexion, Retroformer, and COPPER, and separately evaluate ProFA against automated failure-attribution baselines on held-in and held-out Who & When data. Additional experiments study model size, test-set size, trajectory scope, correctness threshold, and component ablations.
The work targets a practical failure mode in multi-agent systems: feedback can be wasted on agents that did not cause the failure, potentially confusing future behavior. If the reported pattern holds, diagnosing the first consequential mistake and concentrating correction on its owner could make reflective systems more useful under limited inference or training budgets, especially for multi-step question answering, chart analysis, and web interaction. The value is conditional on the paper’s task-specific prompts, model choices, external services, failure annotations, and evaluation setup, and the fixed paper does not provide a verified implementation snapshot for direct reproduction here.
论文中的结论可在「研究结论」中查看。