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

• URL: http://arxiv.org/abs/2606.19980v1
• Date: Thu, 18 Jun 2026 09:21:27 GMT
• Title: ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
• Abstract summary: ENPIRE is a harness framework for coding agents that instantiates a physical feedback routine with four core modules.<n>Powered by ENPIRE, frontier coding agents can autonomously train a policy to achieve a 99% success rate on challenging, dexterous manipulation tasks.
• Score: 40.75426390954145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• A Few Words Go a Long Way: Language Guided Robot Policy Synthesis [9.088404024682706]
  ARCHITECT is a framework that treats robot policy acquisition as an interactive program synthesis task.<n>We introduce an iterative process where a human supervisor provides natural language corrections to steer the policy.<n>In a benchmark evaluation on a Franka Panda robot, ARCHITECT outperforms state-of-the-art VLA models.
  arXiv  Detail & Related papers  (2026-07-26T18:00:02Z)
• Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation [0.0]
  We present Act-Observe-Rewrite (AOR), a framework in which an LLM agent improves a robot manipulation policy.<n>AOR makes the full low-level motor control implementation the unit of LLM reasoning.<n>We report promising results, with the agent achieving high success rates without demonstrations, reward engineering, or gradient updates.
  arXiv  Detail & Related papers  (2026-03-03T22:15:55Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• GRAPPA: Generalizing and Adapting Robot Policies via Online Agentic Guidance [15.774237279917594]
  We propose an agentic framework for robot self-guidance and self-improvement.<n>Our framework iteratively grounds a base robot policy to relevant objects in the environment.<n>We demonstrate that our approach can effectively guide manipulation policies to achieve significantly higher success rates.
  arXiv  Detail & Related papers  (2024-10-09T02:00:37Z)
• A Roadmap Towards Automated and Regulated Robotic Systems [4.6015001632772545]
  We argue that the unregulated generative processes from AI is fitted for low level end tasks. We propose a roadmap that can lead to fully automated and regulated robotic systems.
  arXiv  Detail & Related papers  (2024-03-21T00:14:53Z)
• SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning [82.46975428739329]
  We develop a library containing a sample efficient off-policy deep RL method, together with methods for computing rewards and resetting the environment.<n>We find that our implementation can achieve very efficient learning, acquiring policies for PCB board assembly, cable routing, and object relocation.<n>These policies achieve perfect or near-perfect success rates, extreme robustness even under perturbations, and exhibit emergent robustness recovery and correction behaviors.
  arXiv  Detail & Related papers  (2024-01-29T10:01:10Z)
• Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems [79.07468367923619]
  We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC) We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards. We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
  arXiv  Detail & Related papers  (2022-09-19T16:49:32Z)
• Verifying Learning-Based Robotic Navigation Systems [61.01217374879221]
  We show how modern verification engines can be used for effective model selection. Specifically, we use verification to detect and rule out policies that may demonstrate suboptimal behavior. Our work is the first to demonstrate the use of verification backends for recognizing suboptimal DRL policies in real-world robots.
  arXiv  Detail & Related papers  (2022-05-26T17:56:43Z)
• XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees [55.9643422180256]
  We present a novel sensor-based learning navigation algorithm to compute a collision-free trajectory for a robot in dense and dynamic environments. Our approach uses deep reinforcement learning-based expert policy that is trained using a sim2real paradigm. We highlight the benefits of our algorithm in simulated environments and navigating a Clearpath Jackal robot among moving pedestrians.
  arXiv  Detail & Related papers  (2021-04-22T01:33:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.