# ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

arXiv: https://arxiv.org/abs/2606.19980 · HTML: https://mlsanity.com/paper/2606.19980/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 37 of its 51 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 37)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning](https://mlsanity.com/paper/2410.21845/) (2024)
- [Text2Reward: Reward Shaping with Language Models for Reinforcement Learning](https://mlsanity.com/paper/2309.11489/) (2023)
- [Learning to Walk via Deep Reinforcement Learning](https://mlsanity.com/paper/1812.11103/) (2018)
- [SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning](https://mlsanity.com/paper/2401.16013/) (2024)

## Built on by (most cited first, 30 of 38)

- [The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement](https://mlsanity.com/paper/2609.11873/) (2026)
- [Towards the Harness of Embodied Agents](https://mlsanity.com/paper/2608.11246/) (2026)
- [EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics](https://mlsanity.com/paper/2609.27308/) (2026)
- [Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents](https://mlsanity.com/paper/2610.02204/) (2026)
- [Agora: Git as Shared Memory for Collective AutoResearch](https://mlsanity.com/paper/2609.18094/) (2026)
- [Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation](https://mlsanity.com/paper/2609.20822/) (2026)
- [RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning](https://mlsanity.com/paper/2609.29394/) (2026)
- [What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery](https://mlsanity.com/paper/2609.31760/) (2026)
- [InSight: Self-Guided Skill Acquisition via Steerable VLAs](https://mlsanity.com/paper/2606.24884/) (2026)
- [You Don't Need To Stay in The Loop: An Agentic Robotics Loop for Robot-Policy Improvement](https://mlsanity.com/paper/2608.07555/) (2026)
- [RAPID: Robot Agentic Programming from Demonstrations](https://mlsanity.com/paper/2609.30249/) (2026)
- [RLE-Bench: A Qualifying Exam for Coding Agents as Robot Learning Engineers](https://mlsanity.com/paper/2609.34210/) (2026)
- [Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents](https://mlsanity.com/paper/2609.39304/) (2026)
- [RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments](https://mlsanity.com/paper/2610.12424/) (2026)
- [Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills](https://mlsanity.com/paper/2608.01851/) (2026)
- [SUN: Agentic Robot Policy Learning with Persistent Task Programs](https://mlsanity.com/paper/2608.31167/) (2026)
- [StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation](https://mlsanity.com/paper/2609.20791/) (2026)
- [ARSTAG: An Agentic Real2Sim2Real System for Task-Specific Robot Data Generation](https://mlsanity.com/paper/2609.24563/) (2026)
- [RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents](https://mlsanity.com/paper/2609.32862/) (2026)
- [EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planning](https://mlsanity.com/paper/2609.35047/) (2026)
- [Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence](https://mlsanity.com/paper/2609.35432/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies](https://mlsanity.com/paper/2610.10479/) (2026)
- [Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report](https://mlsanity.com/paper/2607.07370/) (2026)
- [ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Edits](https://mlsanity.com/paper/2608.15138/) (2026)
- [Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI](https://mlsanity.com/paper/2609.04552/) (2026)
- [WetRobo: A Reproducible Robot Kit for Coding Agents in Biological Laboratories](https://mlsanity.com/paper/2609.18435/) (2026)
- [From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation](https://mlsanity.com/paper/2609.19413/) (2026)
- [Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy](https://mlsanity.com/paper/2609.28838/) (2026)
- [DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents](https://mlsanity.com/paper/2609.40306/) (2026)

## Abstract (arXiv)

Achieving dexterous robotic manipulation in the real world heavily relies on human supervision and algorithm engineering, which becomes a central bottleneck in the pursuit of general physical intelligence. Although emerging coding agents can generate code to automate algorithm search, their successes remain largely confined in digital environments. We conjecture that the missing abstraction to automate robotics research is a repeatable feedback loop for real-world policy improvement: reset the scene, execute a policy, verify the outcome, and refine the next iteration. To bridge this gap, we introduce ENPIRE, a harness framework for coding agents that instantiates this physical feedback routine with four core modules: an Environment module (EN) for automatic reset and verification, a Policy Improvement module (PI) that launches policy refinement, a Rollout module (R) to evaluate policies with one or multiple physical robots operating in parallel, and an Evolution module (E) in which coding agents analyze logs, consult literature, improve training infrastructure and algorithm code to address failure modes. This closed-loop system transforms real-world manipulation learning into a controllable optimization procedure, minimizing human effort while allowing fair ablations across training recipe and agent variants. Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks, such as organizing a pin box, fastening a zip tie, and tool use, a process that further accelerates when we dispatch an agent team on a robot fleet. Our results suggest a practical and scalable path toward deploying coding agents to autonomously advancing robotics in the physical world.