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?
SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
SynthDemo‑RL introduces a teacher‑student framework that uses an automated teacher to generate successful manipulation trajectories from simulator‑privileged state, which are then distilled into a Vision‑Language‑Action (VLA) student via supervised fine‑tuning. The student is further refined with PPO using binary task‑success rewards. On the LIBERO‑PRO benchmark, SynthDemo‑RL rescues all 27 previously unsolvable tasks and achieves near‑perfect success rates, matching performance that would otherwise require human demonstrations.
Related stories
arXiv AI
Sep 24
BEE: Intervention-Adaptive Real-World Reinforcement Learning with Vision-Language-Action Models
arXiv:2609.27450v1 Announce Type: cross Abstract: Vision-language-action (VLA) models handle long-horizon manipulation, yet success hinges on a few precision-critical phases where millimeter-scale er...
arXiv AI
Aug 25
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
arXiv:2608.22301v1 Announce Type: cross Abstract: Humans imitate at the level of intent: given a demonstration, we infer its goal and carry it out with whatever tools, objects, and layouts are at han...
arXiv AI
3d ago
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.
arXiv AI
Aug 25
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
The paper introduces RARM, a Reference‑Anchored Reward Model that uses a single successful demonstration to generate dense, progress‑aware rewards for reinforcement learning in robot manipulation. RARM is trained on general‑purpose videos with a contrastive temporal objective, requiring no task‑specific data or reward engineering. During deployment it matches rollout clips to reference clips and rewards only confident forward progress, reducing false positives. Experiments on nine simulated tasks and four real‑world tasks show that RARM achieves the best overall success rates, especially on long‑horizon tasks like cloth folding.
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...
arXiv AI
1d ago
Cooperative Multi-Agent Vision-Language-Action Models via Reinforced Fine Tuning
arXiv:2609.36588v1 Announce Type: cross Abstract: We study reinforcement learning (RL) methods for cooperative multi-agent Vision-Language-Action (VLA) models. This problem is challenging because VLA...
arXiv Machine Learning
Jun 2
Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
arXiv AI
1d ago
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
arXiv:2609.37359v1 Announce Type: cross Abstract: Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves ou...
arXiv Machine Learning
Aug 13
Adaptation of Generalist Robot Policies with Minimal Data
arXiv:2608. 11363v1 Announce Type: cross Abstract: A central goal in robot learning is to move beyond task-specific human data collection toward robots that improve through autonomous interaction.
arXiv Machine Learning
Jul 13
Learning More from Less: Reinforcement Learning from Hindsight
arXiv:2607. 09042v1 Announce Type: new Abstract: Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern.
arXiv AI
Jun 30
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
arXiv:2606. 29892v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning.