TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory

• URL: http://arxiv.org/abs/2606.25161v1
• Date: Tue, 23 Jun 2026 20:49:28 GMT
• Title: TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memory
• Abstract summary: Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows.<n>Existing memory agents actively update external memory through generated write, revise, and delete operations.<n>These updates may omit important information, corrupt existing memory, or introduce unsupported hallucinated content.<n>We propose TrustMem, a framework designed to improve the trustworthiness of memory consolidation.
• Score: 11.528637007309937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents rely on long-term memory to support extended interactions and personalized assistance beyond finite context windows. Existing memory agents actively update external memory through generated write, revise, and delete operations, but these updates may omit important information, corrupt existing memory, or introduce unsupported hallucinated content. Once stored, such errors become persistent system-state failures that can affect future reasoning and generation. In this paper, we propose TrustMem, a framework designed to improve the trustworthiness of memory consolidation. TrustMem relies on a Memory Transition Verifier to evaluate the transition process of memory updates in terms of coverage, preservation, and faithfulness. It further constructs preference pairs among candidate updates under the same memory state, enabling preference-guided reinforcement learning to directly optimize memory updating behaviors. Extensive experiments demonstrate that TrustMem improves both memory utility and reliability: it achieves state-of-the-art results across MemoryAgentBench, HaluMem, and the Mem-alpha validation set, improves HaluMem memory extraction by 12.14 F1 points, and reduces transition-level omission, corruption, and hallucination by 40.1\%, 79.1\%, and 50.0\%, respectively, compared with the strongest baseline for each error type.

Related papers

• TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents [20.123133746969398]
  We introduce TARL, a memory state update framework that maps each statement to one of five executable actions.<n> TARL identifies the affected memory, resolves its temporal scope, compares source reliability, and updates accepted, pending, and rejected ledgers.<n>We also introduce TARL-Mem, a benchmark with fine-grained action labels and next-state targets.
  arXiv  Detail & Related papers  (2026-08-04T14:02:55Z)
• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory [32.49512092540906]
  MemSyco-Bench is a benchmark for evaluating memory-induced sycophancy in agent systems.<n>MemSyco-Bench measures when memory should influence a decision and how valid memory should be used.
  arXiv  Detail & Related papers  (2026-07-01T15:30:33Z)
• MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery [58.64329475683699]
  We argue that long-term memory should be evaluated as an auditable post-interaction artifact.<n>We instantiate this view in MEMPROBE, a benchmark in which a memory-equipped agent assists simulated users.<n>We find that successful assistance and recoverable memory behave as distinct capabilities.
  arXiv  Detail & Related papers  (2026-06-23T13:52:46Z)
• HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents [10.128343847630552]
  HiMPO is a Hindsight-Informed Memory Policy Optimization framework for assigning less-entangled credit to memory-writing actions.<n>We show that HiMPO reduces blame leakage from tool-induced errors and improves attribution fidelity of memory updates.
  arXiv  Detail & Related papers  (2026-06-15T06:49:18Z)
• Beyond Similarity: Trustworthy Memory Search for Personal AI Agents [25.265839311088516]
  We study memory search as a trust boundary in personal AI agents.<n>MemGate is a lightweight and deployable memory plug-in for trustworthy memory search.
  arXiv  Detail & Related papers  (2026-06-04T11:54:29Z)
• WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction [72.1620416874118]
  Multimodal large language models are increasingly deployed as long-horizon agents.<n>Existing benchmarks measure recall over static dialogue, collapse memory into a single end-of-task accuracy, and reduce visual observations to captions.<n>We formulate multimodal agent memory as an Action-World Interaction Loop with an observable four-stage lifecycle.
  arXiv  Detail & Related papers  (2026-05-28T04:27:20Z)
• MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models [56.31411457917676]
  We introduce MemGuard, a type-aware memory framework that preserves functional memory boundaries during memory construction and retrieval.<n>Across hallucination and long-horizon conversation benchmarks, MemGuard improves memory reliability by up to 28.27% while retrieving up to 5.8x fewer memory tokens than prior methods.
  arXiv  Detail & Related papers  (2026-05-27T06:04:19Z)
• 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)
• MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents [29.872311031034368]
  We propose MemCompiler, which reframes memory utilization as State-Conditioned Memory Compilation.<n>Across Alf World, EmbodiedBench, and ScienceWorld, MemCompiler consistently improves over no-memory.
  arXiv  Detail & Related papers  (2026-05-08T11:07:04Z)
• 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)

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.