WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning

• URL: http://arxiv.org/abs/2505.16421v1
• Date: Thu, 22 May 2025 09:07:43 GMT
• Title: WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
• Authors: Zhepei Wei, Wenlin Yao, Yao Liu, Weizhi Zhang, Qin Lu, Liang Qiu, Changlong Yu, Puyang Xu, Chao Zhang, Bing Yin, Hyokun Yun, Lihong Li,
• Abstract summary: WebAgent-R1 is an end-to-end multi-turn reinforcement learning framework for training web agents.<n>Experiments on the WebArena-Lite benchmark demonstrate the effectiveness of WebAgent-R1, boosting the task success rate of Qwen-2.5-3B from 6.1% to 33.9%.<n>In-depth analyses reveal the effectiveness of the thinking-based prompting strategy and test-time scaling through increased interactions for web tasks.
• Score: 37.89715280583421
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While reinforcement learning (RL) has demonstrated remarkable success in enhancing large language models (LLMs), it has primarily focused on single-turn tasks such as solving math problems. Training effective web agents for multi-turn interactions remains challenging due to the complexity of long-horizon decision-making across dynamic web interfaces. In this work, we present WebAgent-R1, a simple yet effective end-to-end multi-turn RL framework for training web agents. It learns directly from online interactions with web environments by asynchronously generating diverse trajectories, entirely guided by binary rewards depending on task success. Experiments on the WebArena-Lite benchmark demonstrate the effectiveness of WebAgent-R1, boosting the task success rate of Qwen-2.5-3B from 6.1% to 33.9% and Llama-3.1-8B from 8.5% to 44.8%, significantly outperforming existing state-of-the-art methods and strong proprietary models such as OpenAI o3. In-depth analyses reveal the effectiveness of the thinking-based prompting strategy and test-time scaling through increased interactions for web tasks. We further investigate different RL initialization policies by introducing two variants, namely WebAgent-R1-Zero and WebAgent-R1-CoT, which highlight the importance of the warm-up training stage (i.e., behavior cloning) and provide insights on incorporating long chain-of-thought (CoT) reasoning in web agents.

Related papers

• How to Train Your LLM Web Agent: A Statistical Diagnosis [102.04125085041473]
  We present the first statistically grounded study on compute allocation for LLM web-agent post-training.<n>Our approach uses a two-stage pipeline, training a Llama 3.1 8B student to imitate a Llama 3.3 70B teacher via supervised fine-tuning (SFT) and on-policy reinforcement learning.<n>Our results show that combining SFT with on-policy RL consistently outperforms either approach alone on both WorkArena and MiniWob++.
  arXiv  Detail & Related papers  (2025-07-05T17:12:33Z)
• WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning [31.455378036113228]
  We introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framework.<n>We employ a structured reward function that evaluates both adherence to output formats and correctness of actions, enabling WorkForceAgent-R1 to implicitly learn robust intermediate reasoning.<n>Experiments on the WorkArena benchmark demonstrate that WorkForceAgent-R1 substantially outperforms SFT baselines by 10.26-16.59%.
  arXiv  Detail & Related papers  (2025-05-28T23:45:28Z)
• WebDancer: Towards Autonomous Information Seeking Agency [69.33360019344083]
  Recent progress in agentic systems underscores the potential for autonomous multi-step research.<n>We present a cohesive paradigm for building end-to-end agentic information seeking agents from a data-centric and training-stage perspective.<n>We instantiate this framework in a web agent based on the ReAct, WebDancer.
  arXiv  Detail & Related papers  (2025-05-28T17:57:07Z)
• WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback [74.82886755416949]
  We identify key reasoning skills essential for effective web agents.<n>We reconstruct the agent's reasoning algorithms into chain-of-thought rationales.<n>Our approach yields significant improvements across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-26T14:03:37Z)
• Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One [28.264011412168347]
  Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents.<n>We propose LLM-Ens, a novel approach that enhances RL model ensemble with task-specific semantic understandings.
  arXiv  Detail & Related papers  (2025-05-21T09:35:43Z)
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning [125.65034908728828]
  Training large language models (LLMs) as interactive agents presents unique challenges.<n>While reinforcement learning has enabled progress in static tasks, multi-turn agent RL training remains underexplored.<n>We propose StarPO, a general framework for trajectory-level agent RL, and introduce RAGEN, a modular system for training and evaluating LLM agents.
  arXiv  Detail & Related papers  (2025-04-24T17:57:08Z)
• AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations [18.820883566002543]
  State-of-the-art multimodal web agents, powered by Multimodal Large Language Models (MLLMs), can autonomously execute many web tasks. Current strategies for building web agents rely on (i) the generalizability of underlying MLLMs and their steerability via prompting, and (ii) large-scale fine-tuning of MLLMs on web-related tasks. We introduce the AdaptAgent framework that enables both proprietary and open-weights multimodal web agents to adapt to new websites and domains using few human demonstrations.
  arXiv  Detail & Related papers  (2024-11-20T16:54:15Z)
• MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning [17.437573206368494]
  Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. Current algorithms suffer from low sample efficiency, limiting their practical applicability. We present MENTOR, a method that improves both the architecture and optimization of RL agents.
  arXiv  Detail & Related papers  (2024-10-19T04:31:54Z)
• AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents [52.13695464678006]
  This study enhances an LLM-based web agent by simply refining its observation and action space. AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively.
  arXiv  Detail & Related papers  (2024-10-17T17:50:38Z)
• Agent Workflow Memory [71.81385627556398]
  We introduce Agent Memory, a method for inducing commonly reused routines. AWM substantially improves the baseline results by 24.6% and 51.1% relative success rate. Online AWM robustly generalizes in cross-task, website, and domain evaluations.
  arXiv  Detail & Related papers  (2024-09-11T17:21:00Z)
• Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents [44.34340798542]
  Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning. Traditional supervised pre-training on static datasets falls short in enabling autonomous agent capabilities. We propose a framework that combines guided Monte Carlo Tree Search (MCTS) search with a self-critique mechanism and iterative fine-tuning on agent interactions.
  arXiv  Detail & Related papers  (2024-08-13T20:52:13Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Retrieval-Augmented Reinforcement Learning [63.32076191982944]
  We train a network to map a dataset of past experiences to optimal behavior. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context. We show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores.
  arXiv  Detail & Related papers  (2022-02-17T02:44:05Z)
• Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication [24.647993999787992]
  We propose a multi-agent online meta-learning framework and cast it as an equivalent two-level nested online convex optimization (OCO) problem. By characterizing the upper bound of the agent-task-averaged regret, we show that the performance of multi-agent online meta-learning depends heavily on how much an agent can benefit from the distributed network-level OCO for meta-model updates via limited communication. We show that a factor of $sqrt1/N$ speedup over the optimal single-agent regret $O(sqrtT)$ after $
  arXiv  Detail & Related papers  (2020-12-15T23:08:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.