Kerestecioglu et al. (2026)

Human-Inspired Memory Architecture for LLM Agents

arXiv

Find It

DOI

Abstract

Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2) interference-based forgetting, (3) engram maturation, (4) reconsolidation upon retrieval, (5) entity knowledge graphs, and (6) hybrid multi-cue retrieval. Each mechanism addresses a specific failure mode of naive memory accumulation. We introduce a synthetic calibration methodology that derives all pipeline thresholds without benchmark data exposure, eliminating a common source of evaluation leakage. We evaluate on two benchmarks. First, a VSCode issue-tracking dataset (13K issues, 120K events) where deduplication-based consolidation achieves 97.2% retention precision with 58% store reduction (+21.8 pp over baseline). Second, the LongMemEval personal-chat benchmark where we conduct the first streaming M-tier evaluation (475 sessions, \~540K unique turns). At a 200K-token context budget, our pipeline matches raw retrieval accuracy (70.1% vs. 71.2%, overlapping 95% CI) while exposing a tunable accuracy/store-size operating curve. At S-tier scale (50 sessions), dedup-based consolidation yields a +13.3 pp improvement in preference recall.

Reference

Kerestecioglu, D., Robsky, A., Vasters, C., Sharma, A., & Kesselman, Y. (2026). Human-Inspired Memory Architecture for LLM Agents. arXiv preprint arXiv:2605.08538.

What Rests on This

Cited in the argument rather than behind a score: this is one of the papers the taxonomy is built on, named where the site explains itself rather than in the findings under a mechanism.