# PhysEvo: Astra Can Act, Let It

arXiv: https://arxiv.org/abs/2610.08995 · HTML: https://mlsanity.com/paper/2610.08995/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 42 references that are in the map.
- First posted on arXiv 6 Oct 2026.

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

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [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)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Automated Design of Agentic Systems](https://mlsanity.com/paper/2408.08435/) (2024)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction](https://mlsanity.com/paper/2306.15724/) (2023)
- [Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation](https://mlsanity.com/paper/2310.02304/) (2023)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [A Self-Improving Coding Agent](https://mlsanity.com/paper/2504.15228/) (2025)
- [AutoHarness: improving LLM agents by automatically synthesizing a code harness](https://mlsanity.com/paper/2603.03329/) (2026)
- [Hyperagents](https://mlsanity.com/paper/2603.19461/) (2026)
- [ASPIRE: Agentic /Skills Discovery for Robotics](https://mlsanity.com/paper/2607.00272/) (2026)
- [Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents](https://mlsanity.com/paper/2607.08448/) (2026)
- [ENPIRE: Agentic Robot Policy Self-Improvement in the Real World](https://mlsanity.com/paper/2606.19980/) (2026)
- [Recursive Harness Self-Improvement](https://mlsanity.com/paper/2607.15524/) (2026)
- [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)
- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [Dream-RSI: Recursive Self-Improvement through Evolving Worlds](https://mlsanity.com/paper/2609.14858/) (2026)
- [EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents](https://mlsanity.com/paper/2605.10332/) (2026)
- [RRSI: Regularized Recursive Self-Improvement of Agent Harnesses](https://mlsanity.com/paper/2609.24972/) (2026)
- [Self-Evolving Embodied Agents via Skill-Harness Evolution](https://mlsanity.com/paper/2608.11350/) (2026)
- [RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning](https://mlsanity.com/paper/2607.18060/) (2026)

## Abstract (arXiv)

Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-improvement (RSI) around a single frozen model. A task agent executes robot tasks; a meta-agent uses the resulting trajectories to diagnose failures, revise tools and skills, and test corrections. The meta-agent can also improve its own diagnostic tools, so retained revisions support both later action and later self-improvement. This process develops joint-level control, evidence-seeking observation, and reusable manipulation skills without model-weight updates or a separately trained action policy. Across 42 RoboDojo tasks, held-out-layout evaluation of retained task-specific deployment versions yields a five-dimension average score of 68.14/100 and 62.00% success, compared with 47.17% for RoboDawn's one-shot Astra agent, the strongest published reference in our comparison. On eight manipulation tasks challenging direct Astra, PhysEvo achieves 55.00% success, compared with 1.25% for the direct-Astra reference. Deploying the simulation-evolved harness on AgileX PiPER and continuing skill revision yields 90.60/100 average score and 84.00% success across 25 trials on five real-world tasks. PhysEvo turns the consequences of action into persistent, testable changes to how a frozen model acts and improves.