English

Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents

Computation and Language 2026-03-06 v1

Abstract

Persistent conversational AI systems face a choice between passing full conversation histories to a long-context large language model (LLM) and maintaining a dedicated memory system that extracts and retrieves structured facts. We compare a fact-based memory system built on the Mem0 framework against long-context LLM inference on three memory-centric benchmarks - LongMemEval, LoCoMo, and PersonaMemv2 - and evaluate both architectures on accuracy and cumulative API cost. Long-context GPT-5-mini achieves higher factual recall on LongMemEval and LoCoMo, while the memory system is competitive on PersonaMemv2, where persona consistency depends on stable, factual attributes suited to flat-typed extraction. We construct a cost model that incorporates prompt caching and show that the two architectures have structurally different cost profiles: long-context inference incurs a per-turn charge that grows with context length even under caching, while the memory system's per-turn read cost remains roughly fixed after a one-time write phase. At a context length of 100k tokens, the memory system becomes cheaper after approximately ten interaction turns, with the break-even point decreasing as context length grows. These results characterize the accuracy-cost trade-off between the two approaches and provide a concrete criterion for selecting between them in production deployments.

Keywords

Cite

@article{arxiv.2603.04814,
  title  = {Beyond the Context Window: A Cost-Performance Analysis of Fact-Based Memory vs. Long-Context LLMs for Persistent Agents},
  author = {Natchanon Pollertlam and Witchayut Kornsuwannawit},
  journal= {arXiv preprint arXiv:2603.04814},
  year   = {2026}
}

Comments

15 pages, 1 figure

R2 v1 2026-07-01T11:04:20.358Z