# Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents

arXiv: https://arxiv.org/abs/2610.02204 · HTML: https://mlsanity.com/paper/2610.02204/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 28 of 28)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (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)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [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)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [GenSim: Generating Robotic Simulation Tasks via Large Language Models](https://mlsanity.com/paper/2310.01361/) (2023)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [GenSim2: Scaling Robot Data Generation with Multi-modal and Reasoning LLMs](https://mlsanity.com/paper/2410.03645/) (2024)
- [Prompt a Robot to Walk with Large Language Models](https://mlsanity.com/paper/2309.09969/) (2023)
- [Re3Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation](https://mlsanity.com/paper/2502.08645/) (2025)
- [Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought](https://mlsanity.com/paper/2305.16744/) (2023)
- [ENPIRE: Agentic Robot Policy Self-Improvement in the Real World](https://mlsanity.com/paper/2606.19980/) (2026)
- [Lifelong Robot Library Learning: Bootstrapping Composable and Generalizable Skills for Embodied Control with Language Models](https://mlsanity.com/paper/2406.18746/) (2024)
- [Playful Agentic Robot Learning](https://mlsanity.com/paper/2606.19419/) (2026)
- [RHO: Your Coding Agent is Secretly a Roboticist](https://mlsanity.com/paper/2606.16458/) (2026)
- [Self-Evolving Embodied Agents via Skill-Harness Evolution](https://mlsanity.com/paper/2608.11350/) (2026)
- [GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents](https://mlsanity.com/paper/2605.29668/) (2026)
- [Scalable Behavior Cloning with Open Data, Training, and Evaluation](https://mlsanity.com/paper/2606.27375/) (2026)
- [Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2603.02623/) (2026)
- [Practice Makes Policies: Bootstrapping and Consolidating Robotic Capabilities from Zero Human Demonstrations](https://mlsanity.com/paper/2607.26809/) (2026)

## Built on by (most cited first, 4 of 4)

- [RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments](https://mlsanity.com/paper/2610.10409/) (2026)
- [SEAR: Self-Evolving Agentic Robotics](https://mlsanity.com/paper/2610.18792/) (2026)
- [RoboSimStudio: An Interactive Toolkit for Human and Agent Rapid Real2Sim of Robot Manipulation Tasks](https://mlsanity.com/paper/2610.18835/) (2026)
- [AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents](https://mlsanity.com/paper/2610.20474/) (2026)

## Abstract (arXiv)

Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with control. We present Reconstruct, Practice, Go Real (RPG), a framework for autonomous improvement of robot execution systems without updating model weights. RPG identifies manipulation capabilities in an offline dataset and constructs related practice tasks in simulation. During practice, RPG uses execution feedback, privileged simulator state, and available dataset videos to diagnose failures. It develops new reusable symbolic skills, refines existing skills, and revises the system prompt based on these diagnoses. Cross-task evaluation tests individual candidate changes and merged revisions before they are retained for reuse. At test time, a multimodal LLM uses the resulting system prompt and skill library to coordinate perception and robot control. On held-out initializations of 22 manipulation tasks, RPG improves task success from 28.6% after the first practice round to 95.0% after 15 rounds, outperforming all evaluated baselines, including ASPIRE (75.5%) and CaP-Agent0 powered by GPT-6 Astra Pro (60.0%). After a common calibration and hardware-adaptation procedure, the frozen system succeeds in all 30 physical trials, with ten trials on each of three tasks. Project Website: https://rpg-robot.github.io/