AgentDropoutV2：通过测试时修正-拒绝剪枝优化多智能体系统中的信息流

AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning

February 26, 2026

作者: Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding, Miao Zhang, Min Zhang

cs.AI

摘要

尽管多智能体系统在复杂推理方面表现出色，但其个体参与者产生的错误信息会引发级联影响。现有解决方案往往依赖僵化的结构工程或昂贵的微调，限制了部署灵活性与适应性。我们提出AgentDropoutV2——一种测试时校正或剔除的剪枝框架，无需重新训练即可动态优化多智能体系统的信息流。该框架作为主动防火墙，通过截取智能体输出并采用检索增强的校正器，基于故障驱动指标池迭代修正错误。该机制利用提炼的故障模式作为先验知识，精准识别潜在错误：可修复的输出经过逐轮校正，不可修复的输出则被剔除以防止错误传播，同时回退策略保障系统完整性。在大量数学基准测试上的实证结果表明，AgentDropoutV2显著提升了多智能体系统的任务性能，在数学基准上平均准确率提升6.3个百分点。该系统还展现出强大的泛化与自适应能力，能根据任务难度动态调整校正强度，并利用上下文感知指标解决广泛错误模式。代码与数据集已发布于https://github.com/TonySY2/AgentDropoutV2。

English

While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information generated by individual participants. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their deployability and adaptability. We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining. Our approach acts as an active firewall, intercepting agent outputs and employing a retrieval-augmented rectifier to iteratively correct errors based on a failure-driven indicator pool. This mechanism allows for the precise identification of potential errors using distilled failure patterns as prior knowledge. Irreparable outputs are subsequently pruned to prevent error propagation, while a fallback strategy preserves system integrity. Empirical results on extensive math benchmarks show that AgentDropoutV2 significantly boosts the MAS's task performance, achieving an average accuracy gain of 6.3 percentage points on math benchmarks. Furthermore, the system exhibits robust generalization and adaptivity, dynamically modulating rectification efforts based on task difficulty while leveraging context-aware indicators to resolve a wide spectrum of error patterns. Our code and dataset are released at https://github.com/TonySY2/AgentDropoutV2.