arXiv AI

Decoupling Planning and Control for Instructable Agents

The paper introduces Instruct-to-Act, a system that decouples planning and control by combining a vision‑language model (VLM) planner with a world‑model controller. The VLM generates sparse, high‑level text instructions, while the controller executes them at high frequency, trained via relabeling rollouts with synthetic instructions and joint optimization of behavior cloning, reward, and world‑model objectives. Across seven embodied environments—including multi‑agent settings—this approach outperforms controller‑only and direct VLM action methods, maintains fast control, and allows swapping pretrained VLM planners without fine‑tuning, achieving competitive results with strong baselines on most tasks.

Hugging Face Trending Papers

Aug 27

Decoupling Planning and Control for Instructable Agents

The paper introduces Instruct-to-Act, a system that decouples high‑level planning from low‑latency control by combining a vision‑language model (VLM) planner with a world‑model controller. The VLM generates sparse, high‑level text instructions, while the controller executes them autonomously at high frequency. Experiments across seven embodied environments, including multi‑agent settings, show that this approach outperforms both controller‑only and direct VLM action‑generation methods, maintains fast control, and allows swapping in different pretrained VLM planners without fine‑tuning.

llms agents reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Aug 6

Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models

arXiv:2608. 04765v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control.

By Houze Xu, Jizhong Li, Ziyi Ye

llms nlp robotics fine-tuning 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

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

Aug 21

EXIMO: VLM Guided Exploration of VLA Policies

arXiv:2608. 19891v1 Announce Type: new Abstract: How to efficiently finetune robot policies to learn new tasks on the fly?

By Bhavya Sukhija, Oliver Groth, Mohit Shridhar, Tim Hertweck, Michael Bloesch, Markus Wulfmeier, Abbas Abdolmaleki, Martin Riedmiller

llms reinforcement-learning robotics fine-tuning multimodal

arXiv AI

Jun 17

PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space

arXiv:2606. 17924v1 Announce Type: cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation.

By Bochen Yang, Lianlei Shan

llms diffusion reinforcement-learning robotics multimodal benchmarks

arXiv AI

Aug 19

LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models

LoopVLA introduces a recurrent Vision‑Language‑Action architecture that learns to refine multimodal representations, predict actions, and estimate when further refinement is unnecessary. By iteratively applying a shared Transformer block and producing a sufficiency score at each step, it decouples refinement from fixed layer indices and aligns confidence scores with action quality through a self‑supervised objective. Experiments on LIBERO, LIBERO‑Plus, and VLA‑Arena demonstrate that LoopVLA reduces model parameters by 45% and boosts inference throughput up to 1.7× while matching or surpassing strong baselines in task success.

By Boyang Shen, Kaixiang Yang, Hao Wang, Qiuyu Yu, Qiang Xie, Qiang Li, Zhiwei Wang

llms robotics efficiency multimodal safety

arXiv AI

Jun 9

BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Models

arXiv:2605. 30226v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulation.

By Zhongxi Chen, Yifan Han, Yanming Shao, Huanming Liu, Congsheng Xu, Xiaoyu Chen, Yao Mu, Wenzhao Lian

reinforcement-learning robotics multimodal

arXiv Machine Learning

Jun 18

Hierarchical Planning with Latent World Models

arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.

By Wancong Zhang, Basile Terver, Artem Zholus, Soham Chitnis, Harsh Sutaria, Mido Assran, Randall Balestriero, Amir Bar, Adrien Bardes, Yann LeCun, Nicolas Ballas

diffusion reinforcement-learning robotics

arXiv AI

Jun 30

Demonstration-Free Robotic Control via LLM Agents

arXiv:2601. 20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift.

By Brian Y. Tsui, Alan Y. Fang, Tiffany J. Hwu

llms agents robotics fine-tuning multimodal benchmarks

arXiv Machine Learning

Jun 10

Task Robustness via Re-Labelling Vision-Action Robot Data

arXiv:2606. 10918v1 Announce Type: cross Abstract: The recent trend in scaling models for robot learning has resulted in impressive policies that can perform various manipulation tasks and generalize to novel scenarios.

By Artur Kuramshin, \"Ozg\"ur Aslan, Cyrus Neary, Glen Berseth

llms robotics multimodal

arXiv AI

Jul 24

Vision-Language-Policy Model for Dynamic Robot Task Planning

arXiv:2512. 19178v2 Announce Type: replace-cross Abstract: Bridging the gap between natural language commands and autonomous execution in unstructured environments remains an open challenge for robotics.

By Jin Wang, Kim Tien Ly, Jacques Cloete, Jin Jin, Nikos Tsagarakis, Ioannis Havoutis

llms agents robotics fine-tuning multimodal

Related stories