Playful Agentic Robot Learning

• URL: http://arxiv.org/abs/2606.19419v1
• Date: Wed, 17 Jun 2026 17:55:23 GMT
• Title: Playful Agentic Robot Learning
• Abstract summary: 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.<n>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.
• Score: 108.08954330298549
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Teach and Grow: An Agent-Centered Architecture for General Robot Learning [20.811152351871257]
  Teach-and-Grow Learning (TGL) is an agent-centered architecture for general robot learning.<n>A multimodal agent turns a few successful demonstrations into reusable Skill Blocks: closed-loop behaviors for meaningful subgoals.<n>New tasks are acquired without task-specific policy retraining.
  arXiv  Detail & Related papers  (2026-08-17T23:45:21Z)
• A Few Words Go a Long Way: Language Guided Robot Policy Synthesis [9.088404024682706]
  ARCHITECT is a framework that treats robot policy acquisition as an interactive program synthesis task.<n>We introduce an iterative process where a human supervisor provides natural language corrections to steer the policy.<n>In a benchmark evaluation on a Franka Panda robot, ARCHITECT outperforms state-of-the-art VLA models.
  arXiv  Detail & Related papers  (2026-07-26T18:00:02Z)
• CODESKILL: Learning Self-Evolving Skills for Coding Agents [13.599750520978988]
  Coding agents produce rich trajectories while solving software-engineering tasks.<n>To enable agent self-evolution, these trajectories can be distilled into reusable procedural skills that compactly encode experience to guide future behavior.<n>We propose CODESKILL, an LLM-based framework that reformulates skill extraction and skill-bank maintenance as a learnable management policy.
  arXiv  Detail & Related papers  (2026-05-25T05:12:49Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• Combee: Scaling Prompt Learning for Self-Improving Language Model Agents [58.781108056413274]
  Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes.<n>It would be efficient and beneficial to run prompt learning in parallel to accommodate the growing trend of learning from many agentic traces or parallel agent executions.<n>We propose Combee, a novel framework to scale parallel prompt learning for self-improving agents.
  arXiv  Detail & Related papers  (2026-04-05T20:07:48Z)
• Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation [0.0]
  We present Act-Observe-Rewrite (AOR), a framework in which an LLM agent improves a robot manipulation policy.<n>AOR makes the full low-level motor control implementation the unit of LLM reasoning.<n>We report promising results, with the agent achieving high success rates without demonstrations, reward engineering, or gradient updates.
  arXiv  Detail & Related papers  (2026-03-03T22:15:55Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [60.04362496037186]
  We present the first controlled study of developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants.<n>Our results show agents can assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• Self-Challenging Language Model Agents [98.62637336505242]
  We propose the Self-Challenging framework for training an agent on high-quality tasks that are generated by itself.<n>The framework achieves over a two-fold improvement in Llama-3.1-8B-Instruct, despite using only self-generated training data.
  arXiv  Detail & Related papers  (2025-06-02T14:23:33Z)
• A Backbone for Long-Horizon Robot Task Understanding [8.889888977376886]
  Therblig-Based Backbone Framework (TBBF) is a structure to enhance interpretability, data efficiency, and generalization in robotic systems.<n>TBBF utilizes expert demonstrations to enable therblig-level task decomposition.<n>During the offline training stage, we developed the Meta-RGate SynerFusion network for accurate therblig segmentation.<n>In the online testing stage, after a one-shot demonstration of a new task is collected, our MGSF network extracts high-level knowledge.
  arXiv  Detail & Related papers  (2024-08-02T15:32:42Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)
• Reinforcement Learning Experiments and Benchmark for Solving Robotic Reaching Tasks [0.0]
  Reinforcement learning has been successfully applied to solving the reaching task with robotic arms. It is shown that augmenting the reward signal with the Hindsight Experience Replay exploration technique increases the average return of off-policy agents.
  arXiv  Detail & Related papers  (2020-11-11T14:00:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.