Generalizable Self-Evolving Memory for Automatic Prompt Optimization

• URL: http://arxiv.org/abs/2603.21520v1
• Date: Mon, 23 Mar 2026 03:29:54 GMT
• Title: Generalizable Self-Evolving Memory for Automatic Prompt Optimization
• Abstract summary: We propose MemAPO, a memory-driven framework for prompt optimization.<n>MemAPO distills successful reasoning trajectories into reusable strategy templates.<n>It organizes incorrect generations into structured error patterns that capture recurrent failure modes.
• Score: 23.58061861097912
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost.

Related papers

• Reflective Prompt Tuning through Language Model Function-Calling [16.552558967042312]
  Reflective Prompt Tuning (RPT) is a framework that simulates the iterative workflow of human prompt engineers.<n>RPT improves over initial prompts by up to 12.9 points, remains competitive with state of the art, and improves confidence calibration.<n>Our analyses show that RPT is especially effective on multi-hop and mathematical reasoning.
  arXiv  Detail & Related papers  (2026-05-20T22:21:29Z)
• MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models [64.2820121997882]
  MIITA is a Memory-Induced Inference-Time Adaptation framework for supervised CL under constrained storage.<n>It stores supervised experiences as compact correction-direction prototypes with semantic anchors, and retrieves them at inference time using semantic and uncertainty-based cues.<n>Experiments show that MIITA consistently improves final performance and mitigates forgetting under fixed memory budgets.
  arXiv  Detail & Related papers  (2026-05-20T03:03:04Z)
• Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory [53.8372503928207]
  Large language model (LLM) agents require long-term user memory for consistent personalization.<n>Existing memory systems mainly rely on static, hand-crafted update rules.<n>We introduce MemCoE, a cognition-inspired two-stage optimization framework that learns how memory should be organized and what information to update.
  arXiv  Detail & Related papers  (2026-05-01T14:45:20Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• GFlowPO: Generative Flow Network as a Language Model Prompt Optimizer [51.31263673158136]
  GFlowPO casts prompt search as a posterior inference problem over latent prompts regularized by a meta-prompted reference-LM prior.<n>GFlowPO consistently outperforms recent discrete prompt optimization baselines.
  arXiv  Detail & Related papers  (2026-02-03T10:30:03Z)
• Error Taxonomy-Guided Prompt Optimization [14.654343320792941]
  We propose Error taxonomy-Guided Prompt Optimization (ETGPO), a prompt optimization algorithm that adopts a top-down approach.<n>ETGPO focuses on the global failure landscape by collecting model errors, categorizing them into a taxonomy, and augmenting the prompt with guidance targeting the most frequent failure modes.<n>ETGPO achieves accuracy that is comparable to or better than state-of-the-art methods, while requiring roughly one third of the optimization-phase token usage and evaluation budget.
  arXiv  Detail & Related papers  (2026-02-01T03:27:44Z)
• AMA: Adaptive Memory via Multi-Agent Collaboration [54.490349689939166]
  We propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities.<n>AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods.
  arXiv  Detail & Related papers  (2026-01-28T08:09:49Z)
• Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization [13.8868879878572]
  A structured optimization approach requires automated or semi-automated procedures to develop improved prompts.<n>Current prompt optimization methods often induce prompt drift, where new prompts fix prior failures but impair performance on previously successful tasks.<n>This study proposes the Hierarchical Prompt Optimization framework, which introduces three innovations: (1) a dynamic attribution mechanism targeting error patterns in training data and prompting history, (2) semantic-unit optimization for editing functional prompt segments, and (3) multimodal-friendly progression supporting both end-to-end LLM and LLM-MLLM.
  arXiv  Detail & Related papers  (2026-01-06T03:34:17Z)
• 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)
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution [0.0]
  We propose a framework that integrates a memory-augmented Reflection RetrievalRAG module and a Self-Adaptive meta-controller.<n>REMO achieves more stable and robust tuning, albeit at the cost of increased computational overhead.
  arXiv  Detail & Related papers  (2025-08-26T07:25:45Z)
• Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration [109.38288333994407]
  Contrastive Prompt Learning (CPL) is a novel framework that fundamentally enhances prompt-task alignment.<n>Our framework establishes new state-of-the-art performance while maintaining parameter efficiency, offering a principled solution for unified image restoration.
  arXiv  Detail & Related papers  (2025-04-14T08:24:57Z)
• Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection [19.020514286500006]
  We propose an Exemplar-Guided Reflection with Memory mechanism to realize more efficient and accurate prompt optimization.<n>Specifically, we design an exemplar-guided reflection mechanism where the feedback generation is additionally guided by the generated exemplars.<n> Empirical evaluations show our method surpasses previous state-of-the-arts with less optimization steps.
  arXiv  Detail & Related papers  (2024-11-12T00:07:29Z)

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.