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

arXiv: https://arxiv.org/abs/2505.03792 · HTML: https://mlsanity.com/paper/2505.03792/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 1 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 45)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Reinforcement Learning with Deep Energy-Based Policies](https://mlsanity.com/paper/1702.08165/) (2017)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [AppAgent: Multimodal Agents as Smartphone Users](https://mlsanity.com/paper/2312.13771/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Android in the Wild: A Large-Scale Dataset for Android Device Control](https://mlsanity.com/paper/2307.10088/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)

## Built on by (most cited first, 18 of 18)

- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [UI-Venus Technical Report: Building High-performance UI Agents with RFT](https://mlsanity.com/paper/2508.10833/) (2025)
- [Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2602.22817/) (2026)
- [Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.26684/) (2026)
- [AgentOCR: Reimagining Agent History via Optical Self-Compression](https://mlsanity.com/paper/2601.04786/) (2026)
- [Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training](https://mlsanity.com/paper/2602.19225/) (2026)
- [Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems](https://mlsanity.com/paper/2602.08847/) (2026)
- [Mano Technical Report](https://mlsanity.com/paper/2509.17336/) (2025)
- [Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.22995/) (2026)
- [ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning](https://mlsanity.com/paper/2510.12693/) (2025)
- [Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2607.22724/) (2026)
- [RoboAgent: Chaining Basic Capabilities for Embodied Task Planning](https://mlsanity.com/paper/2604.07774/) (2026)
- [SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training](https://mlsanity.com/paper/2606.02355/) (2026)
- [StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction](https://mlsanity.com/paper/2605.06642/) (2026)
- [Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse](https://mlsanity.com/paper/2605.09965/) (2026)
- [Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions](https://mlsanity.com/paper/2601.07516/) (2026)
- [Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents](https://mlsanity.com/paper/2609.38805/) (2026)
- [STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents](https://mlsanity.com/paper/2610.20390/) (2026)

## Abstract (arXiv)

Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform uncertainty to all tokens, CoSo leverages counterfactual reasoning to dynamically assess the causal influence of individual tokens on post-processed actions. By prioritizing the exploration of action-critical tokens while reducing the impact of semantically redundant or low-impact tokens, CoSo enables a more targeted and efficient online rollout process. We provide theoretical analysis proving CoSo's convergence and policy improvement guarantees, and extensive empirical evaluations supporting CoSo's effectiveness. Our results across a diverse set of agent tasks, including Android device control, card gaming, and embodied AI, highlight its remarkable ability to enhance exploration efficiency and deliver consistent performance gains. The code is available at https://github.com/langfengQ/CoSo.