AI RESEARCH
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
arXiv CS.AI
•
ArXi:2602.23258v2 Announce Type: replace 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.