While Multi-Agent Systems (MAS) excel in complex reasoning, they suffer from the cascading impact of erroneous information from individual agents. Current solutions often resort to rigid structural engineering or expensive fine-tuning, limiting their adaptability. We propose AgentDropoutV2 (ADv2), a test-time rectify-or-reject pruning framework that dynamically optimizes MAS information flow. Acting as an active firewall, ADv2 intercepts agent outputs and employs a retrieval-augmented rectifier to iteratively correct errors. This rectification is guided by an indicator pool, which is constructed offline by distilling error patterns from historical MAS failure trajectories. Irreparable outputs are subsequently pruned to prevent error propagation. Empirical results demonstrate that ADv2 significantly boosts performance on both fixed and dynamic MAS frameworks, achieving average accuracy gains of 6.39 and 2.28 percentage points on extensive math and code benchmarks, respectively. Furthermore, ADv2 exhibits remarkable adaptivity, dynamically modulating rectification efforts based on task difficulty to resolve a wide spectrum of error patterns. Our code is released at https://github.com/TonySY2/AgentDropoutV2.

翻译：尽管多智能体系统（MAS）在复杂推理任务中表现卓越，但个体智能体错误信息的级联效应始终困扰着系统性能。现有解决方案多采用僵化的结构工程或高成本的微调方法，限制了其适应性。我们提出AgentDropoutV2（ADv2）——一种测试时修正或剪枝框架，可动态优化MAS信息流。作为主动防火墙，ADv2拦截智能体输出，并采用检索增强修正器迭代纠错。该校正过程由离线构建的指示池引导，该池通过从历史MAS故障轨迹中蒸馏错误模式生成。不可修复的输出将被剪除以防止错误传播。实验结果表明，ADv2在固定和动态MAS框架上均显著提升性能，在广泛数学与代码基准测试中分别实现6.39和2.28个百分点的平均准确率提升。此外，ADv2展现出卓越自适应性，能根据任务难度动态调节校正力度，解决多样错误模式。代码已开源至https://github.com/TonySY2/AgentDropoutV2。