Cover Image

Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Lang, Tan, Weihao, Lyu, Zhiyi, Zheng, Longtao, Xu, Haiyang, Yan, Ming, Huang, Fei, An, Bo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
by: Feng, Lang, et al.
Published: (2026)

True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning
by: Tan, Weihao, et al.
Published: (2024)

AgentOCR: Reimagining Agent History via Optical Self-Compression
by: Feng, Lang, et al.
Published: (2026)

AgentStudio: A Toolkit for Building General Virtual Agents
by: Zheng, Longtao, et al.
Published: (2024)

VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought
by: Jiang, Chaoya, et al.
Published: (2025)

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
by: Wang, Junyang, et al.
Published: (2025)

Mobile-Agent-V: A Video-Guided Approach for Effortless and Efficient Operational Knowledge Injection in Mobile Automation
by: Wang, Junyang, et al.
Published: (2025)

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning
by: Ai, Qihang, et al.
Published: (2025)

ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Prompt
by: Zeng, Fanhu, et al.
Published: (2024)

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning
by: Lu, Zhengxi, et al.
Published: (2025)

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
by: Gu, Jihao, et al.
Published: (2025)

CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM
by: Zhou, Kangjie, et al.
Published: (2026)

Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
by: Wang, Junyang, et al.
Published: (2024)

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
by: Chen, Keyu, et al.
Published: (2026)

Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
by: Gao, Zhi, et al.
Published: (2024)

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning
by: Wu, Xiefeng, et al.
Published: (2025)

FishBargain: An LLM-Empowered Bargaining Agent for Online Fleamarket Platform Sellers
by: Kong, Dexin, et al.
Published: (2025)

Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback
by: Li, Gen, et al.
Published: (2025)

Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception
by: Wang, Junyang, et al.
Published: (2024)

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
by: Wang, Kangrui, et al.
Published: (2025)

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment
by: Song, Feifan, et al.
Published: (2024)

Fine-Tuning Language Models with Reward Learning on Policy
by: Lang, Hao, et al.
Published: (2024)

TRELM: Towards Robust and Efficient Pre-training for Knowledge-Enhanced Language Models
by: Yan, Junbing, et al.
Published: (2024)

Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
by: Wang, Zhenhailong, et al.
Published: (2025)

TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning
by: Zhang, Liang, et al.
Published: (2024)

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
by: Xue, Zhenghai, et al.
Published: (2025)

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents
by: Zhang, Yimeng, et al.
Published: (2025)

LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting
by: Li, Yewen, et al.
Published: (2026)

Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning
by: Wu, Qingyuan, et al.
Published: (2025)

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
by: Zheng, Longtao, et al.
Published: (2023)

Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
by: Yu, Le, et al.
Published: (2024)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
by: Hu, Xuhao, et al.
Published: (2026)

VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
by: Xu, Runsen, et al.
Published: (2024)

SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals
by: Zheng, Haoran, et al.
Published: (2024)

Beyond Graph Model: Reliable VLM Fine-Tuning via Random Graph Adapter
by: Jiang, Bo, et al.
Published: (2025)

Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning
by: Wang, Wentao, et al.
Published: (2025)

Sample-Efficient Counterfactual Tuning for Compressor Pressure Control
by: Guerrero, Margarita A., et al.
Published: (2025)

EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection
by: Lei, Qinqian, et al.
Published: (2024)

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning
by: Zhang, Chubin, et al.
Published: (2025)

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs
by: Lyu, Zhiyi, et al.
Published: (2025)