# RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning

arXiv: https://arxiv.org/abs/2609.29394 · HTML: https://mlsanity.com/paper/2609.29394/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 25 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 23 of 23)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (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)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation](https://mlsanity.com/paper/2306.11706/) (2023)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (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)
- [RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2603.11558/) (2026)
- [Playful Agentic Robot Learning](https://mlsanity.com/paper/2606.19419/) (2026)
- [GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks](https://mlsanity.com/paper/2607.05369/) (2026)
- [Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment](https://mlsanity.com/paper/2311.01059/) (2023)
- [ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents](https://mlsanity.com/paper/2604.10096/) (2026)
- [WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents](https://mlsanity.com/paper/2606.18847/) (2026)
- [VIA: Visual Interface Agent for Robot Control](https://mlsanity.com/paper/2607.11119/) (2026)

## Built on by (most cited first, 3 of 3)

- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena](https://mlsanity.com/paper/2610.00854/) (2026)
- [SEAR: Self-Evolving Agentic Robotics](https://mlsanity.com/paper/2610.18792/) (2026)

## Abstract (arXiv)

General-purpose robot agents must learn from experience, transfer to new tasks, and act efficiently. Code as Policies (CaP) methods generate and repair programs at runtime, incurring latency and entangling reusable mechanisms with task-specific decisions. We introduce RACaP, an agentic framework that moves coding to evolution and uses a Reasoning-and-Acting (ReAct) loop to call frozen, typed Policy APIs at deployment. A two-phase strategy combines capability curriculum learning with autonomous self-evolution to improve the APIs, the ReAct harness, and experience memory. The APIs encode reusable physical mechanisms while exposing arguments for runtime adaptation. ReAct combines task-specific working memory, long-term experience memory, and visual feedback to select actions, verify outcomes, and recover from failures without modifying source code. RACaP achieves 54.4% success on LIBERO-90, 45.0% on zero-shot LIBERO-PRO, and 46.0% on LIBERO-Long, compared with at most 4.0% for CaP baselines on long-horizon tasks. On LIBERO-PRO, it achieves 2.5 times the success rate of CaP baselines and a 1.9-fold speedup in median policy time. For efficient on-robot deployment, rejection-sampled fine-tuning distills GPT-5.6 ReAct decisions into Qwen3-VL-8B-Instruct, yielding a 13.2-fold per-decision inference speedup and reducing repeated physical calls from 16 to 4. These results show that separating reusable code from runtime decisions supports continued evolution, effective transfer, and efficient long-horizon control.