AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems
This study addresses the persistent reasoning errors in multi-agent systems caused by memory contamination and scope collapse. To mitigate these issues, we propose a dynamic reliability governance framework that transitions from static storage paradigms to a dynamic governance loop. Specifically, an asymmetric consolidation mechanism is introduced to preserve coordination scope, complemented by multi-scale confidence-aware evaluation with paired replay verification. Furthermore, downstream impact optimization is leveraged to refine high-risk knowledge auditing strategies under limited budgets. Experimental results demonstrate that the proposed method achieves state-of-the-art performance across most benchmarks, outperforming the strongest baseline by 10.23 percentage points. Ablation studies confirm the critical contribution of the scope protection mechanism, whose removal incurs a substantial accuracy degradation of 16.89 percentage points.