# Get Experience from Practice: LLM Agents with Record & Replay

arXiv: https://arxiv.org/abs/2505.17716 · HTML: https://mlsanity.com/paper/2505.17716/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 58 of its 82 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 58)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [ReTool: Reinforcement Learning for Strategic Tool Use in LLMs](https://mlsanity.com/paper/2504.11536/) (2025)
- [Absolute Zero: Reinforced Self-play Reasoning with Zero Data](https://mlsanity.com/paper/2505.03335/) (2025)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition](https://mlsanity.com/paper/2504.21801/) (2025)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.19470/) (2025)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks](https://mlsanity.com/paper/2501.11733/) (2025)
- [Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems](https://mlsanity.com/paper/2504.01990/) (2025)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster](https://mlsanity.com/paper/2304.03208/) (2023)
- [AirGapAgent: Protecting Privacy-Conscious Conversational Agents](https://mlsanity.com/paper/2405.05175/) (2024)
- [LLMs Will Always Hallucinate, and We Need to Live With This](https://mlsanity.com/paper/2409.05746/) (2024)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models](https://mlsanity.com/paper/2504.04717/) (2025)
- [Efficient Inference for Large Reasoning Models: A Survey](https://mlsanity.com/paper/2503.23077/) (2025)
- [SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning](https://mlsanity.com/paper/2503.11951/) (2025)
- [The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections](https://mlsanity.com/paper/2504.11281/) (2025)
- [Explore, Select, Derive, and Recall: Augmenting LLM with Human-like Memory for Mobile Task Automation](https://mlsanity.com/paper/2312.03003/) (2023)
- [ACE: A Security Architecture for LLM-Integrated App Systems](https://mlsanity.com/paper/2504.20984/) (2025)
- [I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2503.18878/) (2025)
- [Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use](https://mlsanity.com/paper/2504.04736/) (2025)

## Built on by (most cited first, 23 of 23)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [Memp: Exploring Agent Procedural Memory](https://mlsanity.com/paper/2508.06433/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows](https://mlsanity.com/paper/2602.14849/) (2026)
- [Trajectory-Informed Memory Generation for Self-Improving Agent Systems](https://mlsanity.com/paper/2603.10600/) (2026)
- [AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library](https://mlsanity.com/paper/2510.18428/) (2025)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore](https://mlsanity.com/paper/2603.20625/) (2026)
- [MobiAgent: A Systematic Framework for Customizable Mobile Agents](https://mlsanity.com/paper/2509.00531/) (2025)
- [PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning](https://mlsanity.com/paper/2602.13691/) (2026)
- [What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment](https://mlsanity.com/paper/2510.08847/) (2025)
- [Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs](https://mlsanity.com/paper/2602.02556/) (2026)
- [PreAct: Computer-Using Agents that Get Faster on Repeated Tasks](https://mlsanity.com/paper/2606.17929/) (2026)
- [Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents](https://mlsanity.com/paper/2511.14780/) (2025)
- [Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory](https://mlsanity.com/paper/2605.15384/) (2026)
- [HippoSpark: An On-Demand Experience System for LLM Reasoning](https://mlsanity.com/paper/2606.29929/) (2026)
- [Translator vs. Challenger: Adversarial Agentic Learning for C-to-Rust Translation](https://mlsanity.com/paper/2609.15381/) (2026)
- [Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics](https://mlsanity.com/paper/2609.19947/) (2026)
- [Chronicle: Cut-Point Replay for Regression Testing of LLM Agents](https://mlsanity.com/paper/2609.20625/) (2026)
- [When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution](https://mlsanity.com/paper/2609.35808/) (2026)
- [Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents](https://mlsanity.com/paper/2610.04375/) (2026)
- [DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents](https://mlsanity.com/paper/2610.11707/) (2026)

## Abstract (arXiv)

AI agents, empowered by Large Language Models (LLMs) and communication protocols such as MCP and A2A, have rapidly evolved from simple chatbots to autonomous entities capable of executing complex, multi-step tasks, demonstrating great potential. However, the LLMs' inherent uncertainty and heavy computational resource requirements pose four significant challenges to the development of safe and efficient agents: reliability, privacy, cost and performance. Existing approaches, like model alignment, workflow constraints and on-device model deployment, can partially alleviate some issues but often with limitations, failing to fundamentally resolve these challenges. This paper proposes a new paradigm called AgentRR (Agent Record & Replay), which introduces the classical record-and-replay mechanism into AI agent frameworks. The core idea is to: 1. Record an agent's interaction trace with its environment and internal decision process during task execution, 2. Summarize this trace into a structured "experience" encapsulating the workflow and constraints, and 3. Replay these experiences in subsequent similar tasks to guide the agent's behavior. We detail a multi-level experience abstraction method and a check function mechanism in AgentRR: the former balances experience specificity and generality, while the latter serves as a trust anchor to ensure completeness and safety during replay. In addition, we explore multiple application modes of AgentRR, including user-recorded task demonstration, large-small model collaboration and privacy-aware agent execution, and envision an experience repository for sharing and reusing knowledge to further reduce deployment cost.