让多智能体系统实时自检纠错，防止错误蔓延。
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction
- 通过预测下一步嵌入检测异常，结合原型先验增强早期判断
- 在Who&When数据集上提升8.47%的错误检测AUC-ROC
- 适用于各类多智能体架构，修正代价低，适合高可靠性场景
基于大语言模型的多智能体系统（MAS）在协作解题中表现优异，但对级联错误敏感：单个错误步骤可能跨代理传播并破坏整体流程。本文提出MASC，一种元认知框架，赋予MAS实时、无监督、逐步级别的错误检测与自纠正能力。MASC将检测重构为历史条件下的异常评分，采用两种互补设计：(1) 下一步执行重建，从查询和交互历史预测下一步嵌入以捕捉因果一致性；(2) 原型引导增强，学习正常步骤嵌入的原型先验，在上下文稀疏（如早期步骤）时稳定重建与异常评分。当标记异常步骤时，MASC触发修正代理在信息向下流动前修改动作代理的输出。在Who&When基准测试中，MASC持续优于所有基线，步级错误检测最高提升8.47% AUC-ROC；接入多种MAS框架后，端到端性能均一致提升，验证了该元认知监控与定向修正可有效缓解错误传播，且开销极小。
原文摘要 · Abstract (English)
Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction. MASC rethinks detection as history-conditioned anomaly scoring via two complementary designs: (1) Next-Execution Reconstruction, which predicts the embedding of the next step from the query and interaction history to capture causal consistency, and (2) Prototype-Guided Enhancement, which learns a prototype prior over normal-step embeddings and uses it to stabilize reconstruction and anomaly scoring under sparse context (e.g., early steps). When an anomaly step is flagged, MASC triggers a correction agent to revise the acting agent's output before information flows downstream. On the Who&When benchmark, MASC consistently outperforms all baselines, improving step-level error detection by up to 8.47% AUC-ROC ; When plugged into diverse MAS frameworks, it delivers consistent end-to-end gains across architectures, confirming that our metacognitive monitoring and targeted correction can mitigate error propagation with minimal overhead.
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。