Search papers, labs, and topics across Lattice.
This paper introduces a framework for LLM-powered agents to learn from execution experiences by extracting actionable insights from trajectories. The framework uses a Trajectory Intelligence Extractor, Decision Attribution Analyzer, and Contextual Learning Generator to produce strategy, recovery, and optimization tips. These learnings are then injected into agent prompts via an Adaptive Memory Retrieval System based on multi-dimensional similarity. Evaluation on the AppWorld benchmark shows up to 14.3 percentage point gains in scenario goal completion, with significant improvements on complex tasks.
LLM agents can now learn from their mistakes and successes in complex tasks, improving performance by up to 28.5% by extracting and applying structured learnings from past execution trajectories.
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).
