Trajectory-Informed Memory Generation for Self-Improving Agent Systems

2026-03-11

AI Summary

This work addresses the tendency of large language model–driven agents to repeat inefficient behaviors, struggle with error recovery, and fail to reuse successful strategies due to the absence of effective experience learning mechanisms. To overcome these limitations, the authors propose a framework that integrates trajectory-aware extraction with decision attribution analysis. The approach automatically generates structured experiences through semantic trajectory parsing and employs a context-aware, multi-dimensional similarity–driven memory retrieval mechanism to adaptively inject three types of guidance: strategic planning, error recovery, and performance optimization. Evaluated on the AppWorld benchmark, the method substantially improves task completion rates, achieving an absolute gain of up to 14.3 percentage points overall and a relative improvement of 149% (+28.5 percentage points) in complex scenarios.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar errors, and miss opportunities to apply successful strategies from past executions. We present a novel framework for automatically extracting actionable learnings from agent execution trajectories and utilizing them to improve future performance through contextual memory retrieval. Our approach comprises four components: (1) a Trajectory Intelligence Extractor that performs semantic analysis of agent reasoning patterns, (2) a Decision Attribution Analyzer that identifies which decisions and reasoning steps led to failures, recoveries, or inefficiencies, (3) a Contextual Learning Generator that produces three types of guidance -- strategy tips from successful patterns, recovery tips from failure handling, and optimization tips from inefficient but successful executions, and (4) an Adaptive Memory Retrieval System that injects relevant learnings into agent prompts based on multi-dimensional similarity. Unlike existing memory systems that store generic conversational facts, our framework understands execution patterns, extracts structured learnings with provenance, and retrieves guidance tailored to specific task contexts. Evaluation on the AppWorld benchmark demonstrates consistent improvements, with up to 14.3 percentage point gains in scenario goal completion on held-out tasks and particularly strong benefits on complex tasks (28.5~pp scenario goal improvement, a 149\% relative increase).

Problem

• agent learning
• execution experience
• trajectory analysis
• memory generation
• performance improvement

Innovation

• trajectory-informed memory
• self-improving agents
• execution trajectory analysis
• contextual learning generation
• adaptive memory retrieval