# Playful Agentic Robot Learning

arXiv: https://arxiv.org/abs/2606.19419 · HTML: https://mlsanity.com/paper/2606.19419/

## Key facts

- Cited by 22 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 9 of its 61 references that are in the map.
- First posted on arXiv 17 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, 9 of 9)

- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer](https://mlsanity.com/paper/2510.03342/) (2025)
- [DrEureka: Language Model Guided Sim-To-Real Transfer](https://mlsanity.com/paper/2406.01967/) (2024)
- [LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery](https://mlsanity.com/paper/2311.02058/) (2023)
- [RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis](https://mlsanity.com/paper/2402.16117/) (2024)
- [Sleep-time Compute: Beyond Inference Scaling at Test-time](https://mlsanity.com/paper/2504.13171/) (2025)
- [MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation](https://mlsanity.com/paper/2602.11337/) (2026)

## Built on by (most cited first, 22 of 22)

- [Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents](https://mlsanity.com/paper/2607.08448/) (2026)
- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents](https://mlsanity.com/paper/2610.02204/) (2026)
- [Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation](https://mlsanity.com/paper/2609.29389/) (2026)
- [RACaP: Agentic Reasoning, Acting, and Coding as Policies for Evolvable Robot Learning](https://mlsanity.com/paper/2609.29394/) (2026)
- [InSight: Self-Guided Skill Acquisition via Steerable VLAs](https://mlsanity.com/paper/2606.24884/) (2026)
- [Sequential Planning via Anchored Robotic Keypoints](https://mlsanity.com/paper/2606.30613/) (2026)
- [Learning and Transferring Closed-Loop Robot Software](https://mlsanity.com/paper/2609.19906/) (2026)
- [World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal](https://mlsanity.com/paper/2609.29964/) (2026)
- [RAPID: Robot Agentic Programming from Demonstrations](https://mlsanity.com/paper/2609.30249/) (2026)
- [SimEX: Simulation-Integrated Robotics AutoResearch](https://mlsanity.com/paper/2609.38982/) (2026)
- [EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution](https://mlsanity.com/paper/2610.10498/) (2026)
- [Teach and Grow: An Agent-Centered Architecture for General Robot Learning](https://mlsanity.com/paper/2608.17209/) (2026)
- [RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents](https://mlsanity.com/paper/2609.32862/) (2026)
- [Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence](https://mlsanity.com/paper/2609.35432/) (2026)
- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation](https://mlsanity.com/paper/2609.36171/) (2026)
- [Encore: Few-Shot Agentic Discovery of Manipulation Strategies](https://mlsanity.com/paper/2609.37359/) (2026)
- [Recursive Video In-Context Learning for Agentic Robot](https://mlsanity.com/paper/2610.06843/) (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)
- [SEAR: Self-Evolving Agentic Robotics](https://mlsanity.com/paper/2610.18792/) (2026)

## Abstract (arXiv)

Current agentic robot systems can write executable Code-as-Policy programs, observe feedback, and revise behavior across multiple attempts, but they remain largely task-driven: reusable skills are acquired only after explicit instructions. We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive. We introduce RATs, Robotics Agent Teams designed for play-time skill acquisition. During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library. At test time, the agent reuses relevant skills from this frozen library to help solve new tasks. Experiments in LIBERO-PRO and MolmoSpaces show that play-learned skills improve held-out downstream tasks over no-play and random-play baselines, with 20.6 and 17.0 percentage-point gains over CaP-Agent0 on LIBERO-PRO and MolmoSpaces, respectively. Moreover, the learned skills can be plugged into other inference-time Code-as-Policy agents by simply retrieving them into the context, improving RoboSuite and real-world transfer by 8.9 and 8.8 points, respectively, without finetuning the underlying model.