Ho-Chan Son

Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell

Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds. Many such systems add a persistent tier storing and recalling reasoning traces, usually validated by an ablation reporting an accuracy gain. We measure b...