arXiv AI

CoDA: Co-Evolution of Data Engines and Action Policies

CoDA is a framework that lets a simulation data engine and an action policy evolve together using a shared memory of environment construction, policy failures, and learning progress. The memory stores validated diagnoses from a vision‑language critic, which are turned into generation programs that recreate challenging scenarios and training programs that help the policy improve. Using this approach, CoDA boosts out‑of‑distribution success on several manipulation tasks, raising success rates from 5.3 % to 27.6 % and achieving up to 84 % success on LIBERO‑Pro under perturbations.

arXiv AI

Sep 28

SUN: Agentic Robot Policy Learning with Persistent Task Programs

The paper introduces SUN (Semantically UNified) Programs, typed executables that translate grounded relations into optimal control objectives, satisfaction predicates, and learning rewards. Using the Kuafu harness, a foundation model orchestrates scene preparation, verification, residual reinforcement learning, and data generation, repairing candidate programs and calibrating reward weights. Across nine multi‑stage manipulation tasks, Kuafu achieves an 82.03% success rate, outperforms learned baselines, generates demonstrations 10.57× faster than human teleoperation, and transfers zero‑shot to physical Franka and Kinova robots.

By Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong

agents reinforcement-learning robotics

arXiv AI

Sep 1

SUN: Persistent Programs For Language-Grounded Control-to-Learning-to-Real Policies

arXiv:2608.31167v1 Announce Type: cross Abstract: Bridging model-based control and learned policies in long-horizon manipulation has harbored a silent disagreement: control executes specified objecti...

By Weiqi Wang, Zhi Li, Yudong Lei, David Martinez, Xiaofeng Gao, Yuxin Jiang, Chenfanfu Jiang, Yingnian Wu, Demetri Terzopoulos, Ran Gong

reinforcement-learning robotics

arXiv AI

Jul 28

A Few Words Go a Long Way: Language Guided Robot Policy Synthesis

arXiv:2607. 23784v1 Announce Type: cross Abstract: While vision-language-action models have demonstrated impressive zero-shot manipulation capabilities, they remain fundamentally black box policies that are difficult to interpret, adapt, or correct when they inevitably fail.

By Daphne Chen, Archit Ritesh Jain, Eric Goossen, Emma Romig, Michael Murray, Nick Walker, Maya Cakmak

llms agents robotics multimodal benchmarks

arXiv Machine Learning

Jun 29

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.

By Raymond Yu, William Huey, Mustafa Mukadam, Anusha Nagabandi, Abhishek Gupta

reinforcement-learning robotics efficiency

arXiv AI

Jul 7

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

arXiv:2607. 05377v1 Announce Type: cross Abstract: While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations.

By Jiaqi Peng, Xiqian Yu, Delin Feng, Yuqiang Yang, Wenzhe Cai, Jing Xiong, Ganlin Yang, Jinliang Zheng, Jiafei Cao, Xueyuan Wei, Jiangmiao Pang, Yuan Shen, Tai Wang

agents robotics fine-tuning multimodal

arXiv AI

Jul 7

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

arXiv:2607. 04265v1 Announce Type: cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception, and contact-dynamics errors in real-world precision tasks, often failing in the final few millimeters of alignment or insertion.

By Angen Ye, Weijie Ke, Xiaofeng Wang, Xinze Chen, Chaojun Ni, Guosheng Zhao, Boyuan Wang, Zheng Zhu, Junjie Xie, Dapeng Zhang

reinforcement-learning robotics safety

arXiv AI

5d ago

OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

OGPO is an Offline Goal‑conditioned Policy Optimization framework designed to improve Vision‑Language‑Action (VLA) models for robotic manipulation. It replaces traditional step‑wise action imitation with adaptive relabeling of trajectories using semantic key states and goal‑conditioned rewards, enabling policies to reach task‑progress states even from off‑demonstration states. Experiments on LIBERO, MetaWorld, LIBERO‑Plus, and the proposed LIBERO‑ReAct benchmark show that OGPO consistently outperforms standard supervised fine‑tuning in terms of robustness and recoverability under distribution shifts.

By Xule Gao, Xi Wang, Zehua Zang, Rui Wang, Changwen Zheng, Chuxiong Sun

robotics fine-tuning multimodal benchmarks

arXiv AI

2d ago

Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies

arXiv:2610.14406v1 Announce Type: cross Abstract: It is widely appreciated that robotic policies require long-term memory to perform complex tasks. However, directly conditioning policies on all past...

By Yilin Wu, Rutav Shah, Shuaiyi Huang, Sumedh A. Sontakke, Homanga Bharadhwaj, Andrea Bajcsy, Max Simchowitz, Guanya Shi

robotics fine-tuning efficiency multimodal

arXiv AI

Sep 30

F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement

arXiv:2609.35575v2 Announce Type: replace-cross Abstract: The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrat...

By Zhuoyuan Yu, Jiacheng Wang, Tianle Liu, Yihua Ren, Peng Yu, Chen Bai, Ziheng Zhang, Yufei Jia, Jindou Jia, Yuhang Zhang, Xinrui Zhang, Shang Yujing, Yuxiang Chen, Chuhao Zhou, Tiancai Wang, Jianfei Yang

agents reinforcement-learning robotics multimodal

arXiv AI

Jun 10

RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning

arXiv:2510. 14828v3 Announce Type: replace Abstract: Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks successfully.

By Jinrui Liu, Bingyan Nie, Boyu Li, Yaran Chen, Yuze Wang, Shunsen He, Haoran Li

llms agents reinforcement-learning robotics fine-tuning benchmarks

Hugging Face Trending Papers

Sep 2

Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM Agents

Large language model (LLM) agents for long-horizon interactive tasks typically follow a ReAct-style protocol, issuing one primitive action per LLM round. While this enables frequent replanning, it is...

llms rag agents reinforcement-learning

arXiv AI

Jul 1

Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models

arXiv:2606. 31846v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control.

By Lang Cao, Renhong Chen, Luyi Li, Peng Wang, Mofan Peng, Yitong Li

reinforcement-learning robotics fine-tuning multimodal benchmarks

Related stories