Generalizable Self-Evolving Memory for Automatic Prompt Optimization

2026-03-22

AI Summary

This work addresses the limited generalization of existing automatic prompt optimization methods, which struggle to accumulate and reuse prompt knowledge across tasks. To overcome this, we propose MemAPO, a novel framework that models prompt optimization as a self-evolving process of experiential learning. MemAPO introduces a dual-memory mechanism that separately stores successful reasoning strategies and error patterns, enabling cross-task knowledge reuse through memory retrieval, self-reflection, and iterative updating. Experimental results demonstrate that MemAPO significantly outperforms state-of-the-art methods across multiple benchmarks while substantially reducing optimization costs.

Technology Category

• Search and Optimization: Learning to Search
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• prompt optimization
• generalization
• memory
• large language models
• knowledge accumulation

Innovation

• memory-driven prompt optimization
• self-evolving memory
• strategy templates
• error patterns
• generalizable prompting