Cover Image

SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Schroeder, Philip, Weng, Thomas, Schmeckpeper, Karl, Rosen, Eric, Hart, Stephen, Biza, Ondrej
Format:	Preprint
Published:	2026
Subjects:	Robotics Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
by: Schroeder, Philip, et al.
Published: (2025)

When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
by: Dodeja, Lakshita, et al.
Published: (2026)

On-Robot Reinforcement Learning with Goal-Contrastive Rewards
by: Biza, Ondrej, et al.
Published: (2024)

You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
by: Patil, Omkar, et al.
Published: (2026)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
by: Xie, Tianbao, et al.
Published: (2023)

Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics
by: Alakuijala, Minttu, et al.
Published: (2024)

LGR2: Language Guided Reward Relabeling for Accelerating Hierarchical Reinforcement Learning
by: Singh, Utsav, et al.
Published: (2024)

Benchmarking Local Language Models for Social Robots using Edge Devices
by: Lamouille, Dorian, et al.
Published: (2026)

REFLEX: Metacognitive Reasoning for Reflective Zero-Shot Robotic Planning with Large Language Models
by: Lin, Wenjie, et al.
Published: (2025)

PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning
by: Holk, Simon, et al.
Published: (2024)

Chain of Uncertain Rewards with Large Language Models for Reinforcement Learning
by: Mo, Shentong
Published: (2026)

From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation
by: Liu, Yibin, et al.
Published: (2026)

CARTIER: Cartographic lAnguage Reasoning Targeted at Instruction Execution for Robots
by: Rivkin, Dmitriy, et al.
Published: (2023)

AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning
by: Dao, Alan, et al.
Published: (2025)

ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation
by: Anwar, Abrar, et al.
Published: (2024)

Evaluation of Habitat Robotics using Large Language Models
by: Li, William, et al.
Published: (2025)

Statler: State-Maintaining Language Models for Embodied Reasoning
by: Yoneda, Takuma, et al.
Published: (2023)

PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning
by: Sun, Yirong, et al.
Published: (2025)

In-Context Learning Enables Robot Action Prediction in LLMs
by: Yin, Yida, et al.
Published: (2024)

Precise Robot Command Understanding Using Grammar-Constrained Large Language Models
by: Huo, Xinyun, et al.
Published: (2026)

Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery
by: Ma, Boyi, et al.
Published: (2025)

Sceniris: A Fast Procedural Scene Generation Framework
by: Shang, Jinghuan, et al.
Published: (2025)

Leveraging Large Language Models in Human-Robot Interaction: A Critical Analysis of Potential and Pitfalls
by: Atuhurra, Jesse
Published: (2024)

Ain't Misbehavin' -- Using LLMs to Generate Expressive Robot Behavior in Conversations with the Tabletop Robot Haru
by: Wang, Zining, et al.
Published: (2024)

Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies
by: Huang, Haojie, et al.
Published: (2024)

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
by: Chen, Yi, et al.
Published: (2024)

Developing Autonomous Robot-Mediated Behavior Coaching Sessions with Haru
by: Jelínek, Matouš, et al.
Published: (2024)

Retrieval-Augmented Hierarchical in-Context Reinforcement Learning and Hindsight Modular Reflections for Task Planning with LLMs
by: Sun, Chuanneng, et al.
Published: (2024)

Robot Tasks with Fuzzy Time Requirements from Natural Language Instructions
by: Sucker, Sascha, et al.
Published: (2024)

Towards Multimodal Social Conversations with Robots: Using Vision-Language Models
by: Janssens, Ruben, et al.
Published: (2025)

RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
by: Li, Huiqiong, et al.
Published: (2026)

Can LLMs Translate Human Instructions into a Reinforcement Learning Agent's Internal Emergent Symbolic Representation?
by: Ma, Ziqi, et al.
Published: (2025)

Vision-Language Interpreter for Robot Task Planning
by: Shirai, Keisuke, et al.
Published: (2023)

VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks
by: Zhang, Shiduo, et al.
Published: (2024)

ALRM: Agentic LLM for Robotic Manipulation
by: Santos, Vitor Gaboardi dos, et al.
Published: (2026)

NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models
by: Zhou, Gengze, et al.
Published: (2024)

Robot Detection System 1: Front-Following
by: Lin, Jinwei
Published: (2024)

Foundation Models for Autonomous Robots in Unstructured Environments
by: Naderi, Hossein, et al.
Published: (2024)

Survey of Design Paradigms for Social Robots
by: Frieske, Rita, et al.
Published: (2024)

PROGrasp: Pragmatic Human-Robot Communication for Object Grasping
by: Kang, Gi-Cheon, et al.
Published: (2023)