# RHO: Your Coding Agent is Secretly a Roboticist

arXiv: https://arxiv.org/abs/2606.16458 · HTML: https://mlsanity.com/paper/2606.16458/

## Key facts

- Cited by 20 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 85 of its 95 references that are in the map.
- First posted on arXiv 15 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 85)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (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)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [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)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [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)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model](https://mlsanity.com/paper/2501.15830/) (2025)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)

## Built on by (most cited first, 20 of 20)

- [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)
- [What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery](https://mlsanity.com/paper/2609.31760/) (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)
- [Learning and Transferring Closed-Loop Robot Software](https://mlsanity.com/paper/2609.19906/) (2026)
- [Coding Agents for Generalized Task and Motion Planning Problems](https://mlsanity.com/paper/2609.30233/) (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)
- [Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools](https://mlsanity.com/paper/2609.39018/) (2026)
- [Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement](https://mlsanity.com/paper/2610.12369/) (2026)
- [Skills in Weights, Memory in Code: Hybrid Learning for Memory-Dependent Robot Manipulation](https://mlsanity.com/paper/2608.09410/) (2026)
- [Loreley: Repository-Scale Program Evolution with Quality-Diversity Search](https://mlsanity.com/paper/2608.19703/) (2026)
- [From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention](https://mlsanity.com/paper/2609.21788/) (2026)
- [Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization](https://mlsanity.com/paper/2609.32394/) (2026)
- [MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation](https://mlsanity.com/paper/2609.38078/) (2026)
- [DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents](https://mlsanity.com/paper/2609.40306/) (2026)
- [InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation](https://mlsanity.com/paper/2610.02196/) (2026)
- [BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation](https://mlsanity.com/paper/2610.07594/) (2026)
- [PhysEvo: Astra Can Act, Let It](https://mlsanity.com/paper/2610.08995/) (2026)
- [RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes](https://mlsanity.com/paper/2610.11480/) (2026)

## Abstract (arXiv)

Code-as-Policies (CaP) has shown that large language models (LLMs) can write code to solve robotics tasks by composing perception, planning, and control primitives. Recent CaP systems, however, rely on multi-turn code-generation loops at test time, which is often infeasible for real-time robot control. We introduce Robotics Harness Optimization (RHO), a novel paradigm in which tool-enabled coding agents, at training time, propose and search for interpretable, neurosymbolic multi-file policy repositories (Repositories-as-Policies) that compose these primitives rather than a single prompt, function, or file. RHO searches with reflective feedback from environment reward and execution rather than teleoperation demonstrations. It generalizes to perturbed pick-and-place settings like LIBERO-PRO, where OpenVLA scores 0.0% and π0.5 averages 12.83%. Using the same low-level primitives, RHO reaches a 45.0% success rate, 2.5x higher than the strongest multi-turn agentic system, and 3.5x higher than π0.5. On Robosuite, RHO sets a new state-of-the-art of 70.0%, exceeding the prior multi-turn record of 68.29% using single-turn execution with no corrective LLM code edits at deployment. When an LLM is used in the control loop, as on RAI's O3DE benchmark, RHO optimizes the deployed agent's multi-file harness of prompts, tools, and control code, improving held-out success from 23.5% to 44.3% with 20% less wall-clock time and 27% fewer tool calls.