# M^star: Every Task Deserves Its Own Memory Harness

arXiv: https://arxiv.org/abs/2604.11811 · HTML: https://mlsanity.com/paper/2604.11811/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 29 of 29)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Augmenting Language Models with Long-Term Memory](https://mlsanity.com/paper/2306.07174/) (2023)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [EvoPrompting: Language Models for Code-Level Neural Architecture Search](https://mlsanity.com/paper/2302.14838/) (2023)
- [MemEvolve: Meta-Evolution of Agent Memory Systems](https://mlsanity.com/paper/2512.18746/) (2025)
- [FLEX: Continuous Agent Evolution via Forward Learning from Experience](https://mlsanity.com/paper/2511.06449/) (2025)
- [PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning](https://mlsanity.com/paper/2511.11562/) (2025)
- [Learning to Continually Learn via Meta-learning Agentic Memory Designs](https://mlsanity.com/paper/2602.07755/) (2026)
- [Evaluating Memory Structure in LLM Agents](https://mlsanity.com/paper/2602.11243/) (2026)

## Built on by (most cited first, 11 of 11)

- [Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference](https://mlsanity.com/paper/2606.05922/) (2026)
- [GUI Agents for Continual Game Generation](https://mlsanity.com/paper/2605.28258/) (2026)
- [Mem-W: Latent Memory-Native GUI Agents](https://mlsanity.com/paper/2605.09317/) (2026)
- [Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents](https://mlsanity.com/paper/2606.05828/) (2026)
- [Rethinking Experience Utilization in Self-Evolving Language Model Agents](https://mlsanity.com/paper/2605.07164/) (2026)
- [Learning to Learn from Multimodal Experience](https://mlsanity.com/paper/2605.16857/) (2026)
- [FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness](https://mlsanity.com/paper/2606.17642/) (2026)
- [Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents](https://mlsanity.com/paper/2609.36892/) (2026)
- [Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance](https://mlsanity.com/paper/2608.03403/) (2026)
- [First Demonstration of Multi-Agent LLM System for Million-Scale Optical Link Management in Global Production AIDCs](https://mlsanity.com/paper/2608.23145/) (2026)
- [Capability-Driven Self-Evolution of Agent Memory](https://mlsanity.com/paper/2610.06361/) (2026)

## Abstract (arXiv)

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.