AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems

Excerpt

arXiv:2610.05176v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems increasingly rely on memory to transform execution trajectories into reusable procedural knowledge. Yet repeated retrieval also makes memory errors persistent: memory pollution arises when outdated, weakly supported, or spuriously successful procedures become recurring components of future reasoning. Multi-agent execution introduces an additional structural risk. Scope collapse occurs when proced