arXiv Machine Learning September 16, 2026 By Tobias Schaffer, Mohab Elkhayat, Daniela Nicklas, Mustafa Almohamad, Elham Al-Fuqara

Intrinsic Robot Rewarding: Reusing VLA Representations for Autonomous Evaluation and Policy Improvement

Read the original on arXiv Machine Learning →

Intrinsic Robot Rewarding (IRR) leverages existing vision‑language‑action (VLA) systems to evaluate a robot’s own outcomes and provide feedback for policy improvement. By using successful demonstration endpoints as task‑specific references and the policy’s frozen visual encoder as the feature space, IRR adds a reference bank and scoring operation to the current pipeline without requiring a separate evaluator or additional perception backbone. The approach aims to reduce integration effort, reward computation cost, and human outcome scoring while enabling learning from the data already available in industrial robot systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 24

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

arXiv:2602. 19313v2 Announce Type: replace-cross Abstract: General-purpose robot learning requires dense, instruction-conditioned feedback that can distinguish meaningful task progress from stalled, failed, or partially completed behavior.

By Shirui Chen, Cole Harrison, Ying-Chun Lee, Angela Jin Yang, Zhongzheng Ren, Lillian J. Ratliff, Jiafei Duan, Dieter Fox, Ranjay Krishna

llms robotics multimodal benchmarks

arXiv Machine Learning

Jun 2

RDA: Reward Design Agent for Reinforcement Learning

arXiv:2606. 01672v1 Announce Type: new Abstract: Reinforcement learning has enabled the acquisition of impressive robotic skills, but typically requires hand-crafted reward functions that are slow to design and difficult to align with human intentions.

By Hojoon Lee, Ajay Subramanian, Ben Abbatematteo, Vijay Veerabadran, Pedro Matias, Karl Ridgeway, Nitin Kamra

llms agents reinforcement-learning robotics multimodal

arXiv AI

Sep 15

ReWeight: Leveraging Human Data for VLA Post-Training via Demonstration Retrieval and Sample Weighting

arXiv:2609.13851v1 Announce Type: cross Abstract: Post-training vision-language-action (VLA) models for specific robots and tasks requires in-domain demonstrations, yet collecting diverse robot data...

By Chenwei Wang, Dianye Huang, Match W. L. Ko, Chenjia Bai, Zhongliang Jiang

robotics multimodal

arXiv AI

Jun 2

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.

By Christian Gumbsch, Leonardo Barcellona, Lennard Sch\"unemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves

llms reinforcement-learning robotics multimodal

arXiv AI

Jul 1

Stage-Transition Dense Reward Modeling for Reinforcement Learning

arXiv:2606. 31377v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to changes in environments and object configurations.

By Yang Yang, Bingjie Chen, Zihan Wang, Yizhe Li, Guoping Pan, Yi Cheng, Houde Liu

agents reinforcement-learning robotics

arXiv AI

Jul 3

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

arXiv:2607. 01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards.

By Yuriy Maksyuta, George Bredis, Ruslan Rakhimov, Daniil Gavrilov

llms reinforcement-learning multimodal benchmarks

One email a morning, machine-written

Related stories

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

RDA: Reward Design Agent for Reinforcement Learning

ReWeight: Leveraging Human Data for VLA Post-Training via Demonstration Retrieval and Sample Weighting

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

Stage-Transition Dense Reward Modeling for Reinforcement Learning

Rank-Then-Act: Reward-Free Control from Frame-Order Progress