Related papers: Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory

Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory

URL: http://arxiv.org/abs/2608.30177v1
Date: Mon, 31 Aug 2026 02:57:08 GMT
Title: Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory
Abstract summary: Memory mechanisms that retain, transform, or expose more information can affect both benign utility and susceptibility to memory poisoning.<n>We present textscMemGauge, a controllable framework that separately varies writing admission, management policy, and retrieval exposure under poisoned conditions.
Score: 21.71796784567462
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Long-term memory is becoming a core capability of LLM agents, enabling personalization and long-horizon interaction. However, memory mechanisms that retain, transform, or expose more information can affect both benign utility and susceptibility to memory poisoning. Existing evaluations typically measure memory utility or attack risk in isolation under fixed configurations, providing limited insight into how stage-specific design choices reshape their trade-off. We present \textsc{MemGauge}, a controllable framework that separately varies writing admission, management policy, and retrieval exposure under matched clean and poisoned conditions. Across 11 LLMs and two long-term memory benchmarks, controlled evaluations reveal three distinct profiles: a threshold-like risk transition during writing, policy-dependent local decoupling during management, and coupled growth of utility and risk during retrieval. We further apply analogous stage-level measurements to four existing memory systems and observe diagnostic associations qualitatively consistent with these profiles. These results show that targeted poisoning risk varies across memory operations and motivate stage-aware evaluation and control of LLM-agent memory.

Related papers

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents [97.19033877543522]
We present a controlled harness evaluation of memory substrates for memory-augmented agents.<n>We instrument 26 performance and efficiency metrics under a unified harness.<n>These findings motivate substrate routing as a necessary component of adaptive agent memory systems.
arXiv Detail & Related papers (2026-08-15T03:29:48Z)
Controlled Memory Interference in Continual LLM Agents [19.630594179909156]
Long-term memory enables AI agents to maintain continuity across sessions, personalize behavior, and evolve through accumulated experience.<n>Existing systems mainly emphasize memory construction and relevance-based retrieval, but several memories may remain simultaneously relevant while differing in state, temporal validity, or authority.<n>We introduce Controlled Memory Interference (CMI), a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships.
arXiv Detail & Related papers (2026-08-07T09:46:19Z)
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents [18.83666486835137]
In deployment, a single agent serves many independent tasks over a long horizon, and memory accumulated during earlier tasks can affect behavior on later, unrelated ones.<n>We introduce a trigger-probe protocol that evaluates a fixed probe set against read-only memory snapshots at varying prefix lengths.<n>We apply this protocol across three deployment scenarios spanning records, memos, forms, and email correspondence and eight memory architectures.
arXiv Detail & Related papers (2026-05-18T04:06:34Z)
MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
arXiv Detail & Related papers (2026-04-17T07:29:52Z)
AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations [61.6579785305668]
AMemGym is an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization.<n>Our framework provides a scalable, diagnostically rich environment for advancing memory capabilities in conversational agents.
arXiv Detail & Related papers (2026-03-02T15:15:11Z)
Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
arXiv Detail & Related papers (2026-01-05T08:24:16Z)
MemOS: A Memory OS for AI System [116.87568350346537]
Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI)<n>Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.<n>MemOS is a memory operating system that treats memory as a manageable system resource.
arXiv Detail & Related papers (2025-07-04T17:21:46Z)
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior [65.70584076918679]
Memory is a critical component in large language model (LLM)-based agents.<n>This paper studies how memory management choices impact the LLM agents' behavior, especially their long-term performance.
arXiv Detail & Related papers (2025-05-21T22:35:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.