MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents

• URL: http://arxiv.org/abs/2604.15774v1
• Date: Fri, 17 Apr 2026 07:29:52 GMT
• Title: MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents
• Abstract summary: 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.
• Score: 78.95081012334116
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent behaviors. Existing evaluation methods have not yet established a standardized framework for measuring memory misevolution. This phenomenon refers to the gradual behavioral drift resulting from repeated exposure to misleading information. To address this gap, we introduce MemEvoBench, the first benchmark evaluating long-horizon memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback. The framework consists of QA-style tasks across 7 domains and 36 risk types, complemented by workflow-style tasks adapted from 20 Agent-SafetyBench environments with noisy tool returns. Both settings employ mixed benign and misleading memory pools within multi-round interactions to simulate memory evolution. Experiments on representative models reveal substantial safety degradation under biased memory updates. Our analysis suggests that memory evolution is a significant contributor to these failures. Furthermore, static prompt-based defenses prove insufficient, underscoring the urgency of securing memory evolution in LLM agents.

Related papers

• Understanding Stage-Wise Utility-Risk Trade-offs in LLM Agent Memory [21.71796784567462]
  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.
  arXiv  Detail & Related papers  (2026-08-31T02:57:08Z)
• 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)
• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents [51.30250860677378]
  We propose MRAgent, a framework that combines an associative memory graph with an active reconstruction mechanism.<n>Running on a Cue-Tag-Content graph, our active reconstruction mechanism integrates reasoning directly into memory access.<n>Experiments on the LoCoMo benchmark and LongMemEval benchmark demonstrate significant improvements over strong baselines.
  arXiv  Detail & Related papers  (2026-06-04T11:29:46Z)
• 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)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory [7.707732051915869]
  Diagnosing agentic memory systems reveals that memory improves reasoning on clean inputs but amplifies reliance on spurious patterns when they are present.<n>We propose CAMEL, a plug-and-play calibration method that operates across diverse memory architectures at both write and retrieval time.<n>Overall, CAMEL offers a principled and lightweight solution toward more reliable agentic memory deployment.
  arXiv  Detail & Related papers  (2026-05-10T05:04:13Z)
• Human-like Working Memory Interference in Large Language Models [13.786393462852395]
  Working memory is fundamental to human reasoning and intelligence.<n>Despite having on the order of 100 billion neurons, both biological and artificial systems exhibit limitations in working memory.<n>We find that although a two-layer transformer can be trained to solve working memory tasks perfectly, a diverse set of pretrained LLMs continues to show working memory limitations.
  arXiv  Detail & Related papers  (2026-04-01T17:19:46Z)
• MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution [52.29303869050117]
  Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction.<n>MemMA is a plug-and-play multi-agent framework that coordinates the memory cycle along both the forward and backward paths.
  arXiv  Detail & Related papers  (2026-03-19T10:15:59Z)
• Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Framework [18.46738022193615]
  Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents.<n>critical concerns regarding memory governance, semantic drift, and privacy vulnerabilities have surfaced.<n>We propose the Stability and Safety-Governed Memory (SSGM) framework, a conceptual governance architecture.
  arXiv  Detail & Related papers  (2026-03-12T10:16:52Z)
• ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents [14.695250837875454]
  We propose a novel actionable memory framework called ActMem.<n>ActMem transforms unstructured dialogue history into a structured causal and semantic graph.<n>It enables agents to deduce implicit constraints and resolve potential conflicts between past states and current intentions.
  arXiv  Detail & Related papers  (2026-02-04T00:54:53Z)
• TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking [32.57514611558346]
  Test-time evolution of agent memory serves as a pivotal paradigm for achieving AGI.<n>Agent safety alignment remains vulnerable to a phenomenon known as Agent Memory Misevolution.<n>We propose TAME, a dual-memory evolutionary framework that separately evolves memory to improve task performance.
  arXiv  Detail & Related papers  (2026-02-03T07:52:26Z)
• Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning [44.94110361062394]
  Decision-making in the real world depends on memory that is both stable and adaptive.<n>Existing Reinforcement Learning benchmarks and memory-augmented agents focus primarily on retention.<n>We introduce a benchmark that explicitly tests continual memory updating under partial observability.
  arXiv  Detail & Related papers  (2026-01-21T15:27:23Z)
• MemGen: Weaving Generative Latent Memory for Self-Evolving Agents [57.1835920227202]
  We propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty.<n>MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition.
  arXiv  Detail & Related papers  (2025-09-29T12:33:13Z)
• Memp: Exploring Agent Procedural Memory [72.41472703974935]
  Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters.<n>We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions.<n>We show that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks.
  arXiv  Detail & Related papers  (2025-08-08T16:20:56Z)
• 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.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.