# WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks

arXiv: https://arxiv.org/abs/2601.02439 · HTML: https://mlsanity.com/paper/2601.02439/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 38 of its 47 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 38)

- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [OpenThoughts: Data Recipes for Reasoning Models](https://mlsanity.com/paper/2506.04178/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning](https://mlsanity.com/paper/2505.24298/) (2025)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [WebCanvas: Benchmarking Web Agents in Online Environments](https://mlsanity.com/paper/2406.12373/) (2024)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [Grounded Reinforcement Learning for Visual Reasoning](https://mlsanity.com/paper/2505.23678/) (2025)
- [Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge](https://mlsanity.com/paper/2506.21506/) (2025)
- [PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://mlsanity.com/paper/2501.10120/) (2025)
- [e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs](https://mlsanity.com/paper/2506.09026/) (2025)
- [Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents](https://mlsanity.com/paper/2412.13194/) (2024)
- [SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent](https://mlsanity.com/paper/2511.16108/) (2025)
- [DeepShop: A Benchmark for Deep Research Shopping Agents](https://mlsanity.com/paper/2506.02839/) (2025)

## Built on by (most cited first, 19 of 19)

- [Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence](https://mlsanity.com/paper/2604.18292/) (2026)
- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL](https://mlsanity.com/paper/2602.22190/) (2026)
- [MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research](https://mlsanity.com/paper/2605.26114/) (2026)
- [Orchard: An Open-Source Agentic Modeling Framework](https://mlsanity.com/paper/2605.15040/) (2026)
- [OpenForgeRL: Train Harness-native Agents in Any Environment](https://mlsanity.com/paper/2607.21557/) (2026)
- [On Training Large Language Models for Long-Horizon Tasks: An Empirical Study of Horizon Length](https://mlsanity.com/paper/2605.02572/) (2026)
- [OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents](https://mlsanity.com/paper/2606.02031/) (2026)
- [Weblica: Scalable and Reproducible Training Environments for Visual Web Agents](https://mlsanity.com/paper/2605.06761/) (2026)
- [OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics](https://mlsanity.com/paper/2606.09826/) (2026)
- [AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents](https://mlsanity.com/paper/2606.05597/) (2026)
- [PRO-CUA: Process-Reward Optimization for Computer Use Agents](https://mlsanity.com/paper/2605.29119/) (2026)
- [SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents](https://mlsanity.com/paper/2607.23263/) (2026)
- [Wuying-Browser-Agent: Real-World Centric Fundamental Long-Horizon Browser Agents](https://mlsanity.com/paper/2608.17319/) (2026)
- [Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling](https://mlsanity.com/paper/2603.02519/) (2026)
- [RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management](https://mlsanity.com/paper/2604.13531/) (2026)
- [Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning](https://mlsanity.com/paper/2605.22642/) (2026)
- [Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks](https://mlsanity.com/paper/2609.08404/) (2026)
- [WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents](https://mlsanity.com/paper/2609.36887/) (2026)

## Abstract (arXiv)

We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains nearly 300,000 tasks with rubric-based evaluations across diverse, real-world websites and difficulty levels. We train agents with a simple reinforcement learning (RL) recipe, which trains on the agent's own interaction traces (rollouts), using task rewards as feedback to guide learning. To enable scaling RL, we speed up sampling of trajectories in WebGym by developing a high-throughput asynchronous rollout system, designed specifically for web agents. Our system achieves a 4-5x rollout speedup compared to naive implementations. Second, we scale the task set breadth, depth, and size, which results in continued performance improvement. Fine-tuning a strong base vision-language model, Qwen-3-VL-8B-Instruct, on WebGym results in an improvement in success rate on an out-of-distribution test set from 26.2% to 42.9%, significantly outperforming agents based on proprietary models such as GPT-4o and GPT-5-Thinking that achieve 27.1% and 29.8%, respectively. This improvement is substantial because our test set consists only of tasks on websites never seen during training, unlike many other prior works on training visual web agents.