LAM is proposed, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a performance model that estimates compaction costs before deployment.
Abstract
Agent memory grows as agents read inputs, reason, and call tools. Longer histories increase inference cost and eventually exceed the context window. LLM-based summarization reduces this history but adds latency and provides no explicit bound on information loss. We propose LAM, a Lossy Agent Memory system with three components: a deterministic deduplication rule with a substitution bound on retrieval scores - a bound on score perturbation, not a certificate of unchanged ranking; a memory manager that preserves the cached prefix and overlaps compaction with inference; and a performance model that estimates compaction costs before deployment. On 600 agent trajectories, LAM removes 22.47% of observation tokens while retaining 99.984% of the measured gold-patch evidence. At a fixed deletion set, the performance model predicts a 71.4x-91.6x end-to-end speedup from removing records before prefill instead of deleting them from a prefilled context. That benefit comes from the schedule rather than the rule and applies to any prefix-preserving test.
This work introduces a unified formulation of context optimization and shows that an agent memory system update can be interpreted as an optimization update procedure over the model's context, and proposes GraphMemory, a lightweight graph-based memory that accumulates, refines, organizes, and connects reusable strategi...
Yehya Farhat, Michael Desmond, Anastasios Kyrillidis· 0 citations
The results suggest that effective long-horizon agent memory depends less on storing more information than on deciding which information should remain active, and that effective long-horizon agent memory depends less on storing more information than on deciding which information should remain active.
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...
Ho-Chan Son, Kyungdoe Han, Jaehan Koh et al.· 0 citations
Long-horizon agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a neural memory network that supplements the summary with a bounded sequence of soft memory tokens. Given the history and summary, the network...
Han-Chen Xia, Bao-You Chen, Yu-Tang Ge et al.· 0 citations
DolphinBench is presented, a benchmark that evaluates memory directly through an agent's task completion and requires all evaluations to report total cost and latency alongside accuracy, which enables us to evaluate agent memory systems holistically.
Overall, EdgeMem shows that preserving and organizing source evidence provides an effective and efficient foundation for agent memory without generative memory management.
Ze-Yang Cui, Jian-Nong Cao, Zhiyuan Wen et al.· 0 citations