M$^\star$: Every Task Deserves Its Own Memory Harness

• URL: http://arxiv.org/abs/2604.11811v1
• Date: Fri, 10 Apr 2026 03:22:26 GMT
• Title: M$^\star$: Every Task Deserves Its Own Memory Harness
• Abstract summary: Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions.<n>Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding.<n>We introduce M$star$, a method that automatically discovers task-optimized memory harnesses through program evolution.
• Score: 28.900347612231513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M$^\star$, a method that automatically discovers task-optimized memory harnesses through executable program evolution. Specifically, M$^\star$ models an agent memory system as a memory program written in Python. This program encapsulates the data Schema, the storage Logic, and the agent workflow Instructions. We optimize these components jointly using a reflective code evolution method; this approach employs a population-based search strategy and analyzes evaluation failures to iteratively refine the candidate programs. We evaluate M$^\star$ on four distinct benchmarks spanning conversation, embodied planning, and expert reasoning. Our results demonstrate that M$^\star$ improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain. This finding indicates that specializing the memory mechanism for a given task explores a broad design space and provides a superior solution compared to general-purpose memory paradigms.

Related papers

• 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)
• 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)
• EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective [21.66000179149483]
  EvoMemBench is a unified benchmark organized along two axes: memory scope and memory content.<n>We compare 15 representative memory methods with strong long-context baselines under a standardized protocol.<n>Results show that current memory systems are still far from a general solution.
  arXiv  Detail & Related papers  (2026-05-18T13:54:38Z)
• MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search [59.98962867649009]
  We propose MemSearch-o1, an agentic search framework built on reasoning-aligned memory growth and retracing.<n>MemSearch-o1 grows fine-grained memory fragments from memory seed tokens from queries, then retraces and deeply refines the memory via a contribution function, and finally reorganizes a globally connected memory path.
  arXiv  Detail & Related papers  (2026-04-19T05:35:06Z)
• Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents [56.078070829341534]
  Memory-based self-evolution has emerged as a promising paradigm for coding agents.<n>We investigate textbfMemory Transfer Learning (MTL) by harnessing a unified memory pool from heterogeneous domains.
  arXiv  Detail & Related papers  (2026-04-15T15:50:29Z)
• RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design [77.30163153176954]
  RMBench is a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity.<n>Mem-0 is a modular manipulation policy with explicit memory components designed to support controlled ablation studies.<n>We identify memory-related limitations in existing policies and provide empirical insights into how architectural design choices influence memory performance.
  arXiv  Detail & Related papers  (2026-03-01T18:59:59Z)
• Graph-based Agent Memory: Taxonomy, Techniques, and Applications [63.70340159016138]
  Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks.<n>Among diverse paradigms, graph stands out as a powerful structure for agent memory due to the intrinsic capabilities to model relational dependencies.<n>This survey presents a comprehensive review of agent memory from the graph-based perspective.
  arXiv  Detail & Related papers  (2026-02-05T13:49:05Z)
• 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)
• AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation [40.1709026042412]
  We propose AtomMem, which reframes memory management as a dynamic decision-making problem.<n>By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors.<n> Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods.
  arXiv  Detail & Related papers  (2026-01-13T08:22:28Z)
• 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)
• EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory [2.9578217823740065]
  We present EvoMem, a multi-agent framework built on a dual-evolving memory mechanism.<n>We show consistent performance improvements on trip planning, meeting planning, and calendar scheduling.<n>This success underscores the importance of memory in enhancing multi-agent planning.
  arXiv  Detail & Related papers  (2025-11-01T01:38:07Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• Mem-α: Learning Memory Construction via Reinforcement Learning [20.916677456417464]
  Large language model (LLM) agents are constrained by limited context windows.<n>Current memory-augmented agents depend on pre-defined instructions and tools for memory updates.<n>Mem-alpha is a reinforcement learning framework that trains agents to effectively manage complex memory systems.
  arXiv  Detail & Related papers  (2025-09-30T08:02:34Z)
• 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)

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.