# Trajectory-Informed Memory Generation for Self-Improving Agent Systems arXiv: https://arxiv.org/abs/2603.10600 ยท HTML: https://mlsanity.com/paper/2603.10600/ ## Key facts - Cited by 17 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 9 of its 21 references that are in the map. - First posted on arXiv 11 Mar 2026. ## Placed in - LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/) - Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/) ## Builds on (most cited first, 9 of 9) - [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023) - [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025) - [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) - [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025) - [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025) - [Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents](https://mlsanity.com/paper/2502.06975/) (2025) - [Get Experience from Practice: LLM Agents with Record & Replay](https://mlsanity.com/paper/2505.17716/) (2025) - [Episodic memory in AI agents poses risks that should be studied and mitigated](https://mlsanity.com/paper/2501.11739/) (2025) ## Built on by (most cited first, 17 of 17) - [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026) - [SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution](https://mlsanity.com/paper/2605.18401/) (2026) - [Procedural Knowledge at Scale Improves Reasoning](https://mlsanity.com/paper/2604.01348/) (2026) - [Co-Evolving Skill Generation and Policy Optimization](https://mlsanity.com/paper/2606.08755/) (2026) - [What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents](https://mlsanity.com/paper/2607.06184/) (2026) - [View-oriented Conversation Compiler for Agent Trace Analysis](https://mlsanity.com/paper/2603.29678/) (2026) - [RAG over Thinking Traces Can Improve Reasoning Tasks](https://mlsanity.com/paper/2605.03344/) (2026) - [ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systems](https://mlsanity.com/paper/2606.08702/) (2026) - [Metis: Bridging Text and Code Memory for Self-Evolving Agents](https://mlsanity.com/paper/2606.24151/) (2026) - [GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning](https://mlsanity.com/paper/2608.10494/) (2026) - [SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction](https://mlsanity.com/paper/2609.05511/) (2026) - [Mechanistic Attention Guidance for Agent Memory Refinement](https://mlsanity.com/paper/2607.17621/) (2026) - [Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch](https://mlsanity.com/paper/2607.27687/) (2026) - [CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories](https://mlsanity.com/paper/2608.22533/) (2026) - [Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course](https://mlsanity.com/paper/2609.08832/) (2026) - [DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement](https://mlsanity.com/paper/2609.21423/) (2026) - [DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks](https://mlsanity.com/paper/2610.08048/) (2026) ## Abstract (arXiv) 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).