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.

翻译：尽管多智能体系统（MAS）在复杂推理方面表现出色，但其易受单个参与者生成错误信息的级联影响。现有解决方案通常依赖于僵化的结构工程或昂贵的微调，限制了其可部署性与适应性。我们提出AgentDropoutV2，一种测试时修正-拒绝剪枝框架，旨在无需重新训练即可动态优化MAS信息流。该方法充当主动防火墙，拦截智能体输出并采用检索增强修正器，基于故障驱动指示器池迭代纠正错误。该机制允许利用提炼的故障模式作为先验知识，精确识别潜在错误。不可修复的输出随后被剪枝以防止错误传播，同时后备策略保障系统完整性。在广泛数学基准测试上的实证结果表明，AgentDropoutV2显著提升了MAS的任务性能，在数学基准上平均准确率提升6.3个百分点。此外，该系统展现出强大的泛化与自适应能力，能根据任务难度动态调节修正强度，并利用上下文感知指示器解决广泛类型的错误模式。我们的代码与数据集发布于https://github.com/TonySY2/AgentDropoutV2。