MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents

• URL: http://arxiv.org/abs/2608.02113v1
• Date: Mon, 03 Aug 2026 12:10:52 GMT
• Title: MemArbiter: Decision-Time Memory Arbitration for Long-Horizon LLM Agents
• Abstract summary: We propose MemArbiter, a function-aware memory arbitration framework.<n>MemArbiter decomposes interaction histories into atomic items, organizes them into five functional Memory Banks.<n>MemArbiter achieves success rates of 82.8% and 92.5% under 500- and 750-token budgets.
• Score: 14.82470944373943
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents must retain and use cross-step information to act coherently in long-horizon tasks. Existing methods improve memory accessibility, yet action-relevant information may still fail to guide the current decision because it is poorly formed, organized, prioritized, or presented. We call this post-access failure the Memory-Action Gap. We propose MemArbiter, a function-aware memory arbitration framework that addresses the memory-management-induced component of this gap. MemArbiter decomposes interaction histories into atomic items, organizes them into five functional Memory Banks, and combines bank-level demand, item-level relevance, focal-ambient representations, and a temporal presentation gate to dynamically control memory salience. We evaluate MemArbiter on ALFWorld against Flat Retrieval and Flat Recency under unified per-step memory budgets. With an open-weight action-generation model, MemArbiter achieves success rates of 82.8% and 92.5% under 500- and 750-token budgets, outperforming the strongest baseline by 20.9 and 25.4 percentage points, respectively. It also improves post-failure recovery and reduces failed-action repetition and state-action recurrence. These results show that function-aware memory arbitration enables accessible information to guide actions more effectively.

Related papers

• Hindsight Memory-PRM: Supervising Memory Management with Auditable Hindsight Credit [48.811961095386]
  Hindsight Memory-PRM exploits this audit trail twice.<n> offline to train an operation-conditioned memory-utility critic.<n>Online, where retrievals, citations, and one controlled deletion-and-reanswer per probe settle an intervention-calibrated entry-level presence credit.
  arXiv  Detail & Related papers  (2026-08-30T06:53:13Z)
• 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)
• Mechanistic Attention Guidance for Agent Memory Refinement [32.57216046158823]
  We show that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization.<n>We propose Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates.
  arXiv  Detail & Related papers  (2026-07-20T07:17:50Z)
• 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)
• ActiveMem: Distributed Active Memory for Long-Horizon LLM Reasoning [46.225019133047965]
  Memory is essential for enabling large language model (LLM) agents to handle long-horizon reasoning tasks.<n>We propose ActiveMem, a framework that decouples agent memory from the core reasoning process.<n>Experiments on BrowseComp-Plus and GAIA show that ActiveMem achieves state-of-the-art accuracy with significantly reduced overhead.
  arXiv  Detail & Related papers  (2026-06-09T08:03:38Z)
• 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)
• 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)
• MemPO: Self-Memory Policy Optimization for Long-Horizon Agents [52.00646524941419]
  Existing methods typically introduce the external memory module and look up the relevant information from the stored memory.<n>We propose the self-memory policy optimization algorithm (MemPO), which enables the agent to autonomously summarize and manage their memory.<n>MemPO achieves absolute F1 score gains of 25.98% over the base model and 7.1% over the previous SOTA baseline, while reducing token usage by 67.58% and 73.12%.
  arXiv  Detail & Related papers  (2026-02-28T14:43:02Z)
• 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)
• Mem-T: Densifying Rewards for Long-Horizon Memory Agents [23.19373149519922]
  We introduce Mem-T, an autonomous memory agent that interfaces with a lightweight hierarchical memory database to perform dynamic updates and multi-turn retrieval over streaming inputs.<n>We also propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via memory operation tree backpropagation and hindsight credit assignment.
  arXiv  Detail & Related papers  (2026-01-30T14:23:33Z)
• Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management [63.48041801851891]
  Fine-Mem is a unified framework designed for fine-grained feedback alignment.<n> Experiments on Memalpha and MemoryAgentBench demonstrate that Fine-Mem consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-01-13T11:06:17Z)
• 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)

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.