paper-with-me

Papers

Retention Consequence in Lifecycle Memory Control

2026-04-18 · Jiarui Han arxiv

Persistent memory can fail after successful admission: a premise is written, then becomes a silent assumption, and later maintenance treats it as ordinary residue to be compressed, demoted, or evicted. We study this post-admission failure as a lifecycle-control problem. Existing memory systems already perform admission, update, compression, retrieval, and eviction. Our claim is not that such systems lack maintenance, but that retention consequence is often operationalized only indirectly through validity, similarity, recency, frequency, importance, or summarization signals rather than exposed as a separate lifecycle state. We therefore treat confidence as carried-forward validity/support evidence, and introduce strength as an explicit lifecycle state for retention consequence. We operationalize this distinction in StageMem, a small staged controller whose transient, working, and durable stores expose promotion, compression, and eviction pressure points. Across controlled premise-realization, compression, pressure, and implicit-heuristic diagnostics, the experiments separate writing too little, retaining the wrong high-cue content, forgetting costly premises, and preserving everything by saturation. Explicit retention consequence, used through lifecycle settlement, provides a control surface between omission and hoarding. For the targeted post-admission failure mode, the results support a lifecycle view of persistent memory: reliability depends not only on what enters memory, but on whether admission validity and retention consequence remain available during maintenance.

📄 PDF Abstract BibTeX arXiv:2604.16774

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems

2026-02-22 · Emmanuel Bamidele arxiv

Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based retention (e.g., TTL). While TTL bounds item lifetime, it does not bound the…

A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle

2026-04-17 · Zehao Lin, Xixuan Hao, Renyu Fu, Shaobo Cui 외 arxiv

The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric security concerns, characterized by three properties: persist…

Information as Structural Alignment: A Dynamical Theory of Continual Learning

2026-04-08 · Radu Negulescu arxiv

Catastrophic forgetting is not an engineering failure. It is a mathematical consequence of storing knowledge as global parameter superposition. Existing methods, such as regularization, replay, and frozen subnetworks, ad…

Continual Learning

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

2026-07-29 · Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou 외 arxiv

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recal…

PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents

2026-06-03 · Yubo Hou, Jingwei Song, Hongbo Zhang, Zhisheng Chen 외 arxiv

Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet…