# Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory arXiv: https://arxiv.org/abs/2510.19838 ยท HTML: https://mlsanity.com/paper/2510.19838/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 30 of its 49 references that are in the map. - First posted on arXiv 18 Oct 2025. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - 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 30) - [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024) - [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023) - [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024) - [WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models](https://mlsanity.com/paper/2401.13919/) (2024) - [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024) - [OS-ATLAS: A Foundation Action Model for Generalist GUI Agents](https://mlsanity.com/paper/2410.23218/) (2024) - [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024) - [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024) - [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023) - [Agent S: An Open Agentic Framework that Uses Computers Like a Human](https://mlsanity.com/paper/2410.08164/) (2024) - [You Only Look at Screens: Multimodal Chain-of-Action Agents](https://mlsanity.com/paper/2309.11436/) (2023) - [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024) - [OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis](https://mlsanity.com/paper/2412.19723/) (2024) - [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024) - [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024) - [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024) - [AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents](https://mlsanity.com/paper/2410.13825/) (2024) - [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025) - [ScreenAgent: A Vision Language Model-driven Computer Control Agent](https://mlsanity.com/paper/2402.07945/) (2024) - [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024) - [Beyond Browsing: API-Based Web Agents](https://mlsanity.com/paper/2410.16464/) (2024) - [SteP: Stacked LLM Policies for Web Actions](https://mlsanity.com/paper/2310.03720/) (2023) - [A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications](https://mlsanity.com/paper/2506.12594/) (2025) - [Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents](https://mlsanity.com/paper/2502.13012/) (2025) - [AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications](https://mlsanity.com/paper/2508.16279/) (2025) - [MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot](https://mlsanity.com/paper/2404.18074/) (2024) - [Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists](https://mlsanity.com/paper/2506.00042/) (2025) - [Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on Introspection](https://mlsanity.com/paper/2505.22192/) (2025) ## Built on by (most cited first, 6 of 6) - [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025) - [WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment](https://mlsanity.com/paper/2512.12692/) (2025) - [WebNavigator: Global Web Navigation via Interaction Graph Retrieval](https://mlsanity.com/paper/2603.20366/) (2026) - [Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation](https://mlsanity.com/paper/2602.14083/) (2026) - [CI4A: Semantic Component Interfaces for Agents Empowering Web Automation](https://mlsanity.com/paper/2601.14790/) (2026) - [Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns](https://mlsanity.com/paper/2606.17645/) (2026) ## Abstract (arXiv) Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical embodied reasoning in open web environments. However, existing approaches remain limited in reasoning depth and efficiency: vanilla linear methods fail at multi-step reasoning and lack effective backtracking, while other search strategies are coarse-grained and computationally costly. We introduce Branch-and-Browse, a fine-grained web agent framework that unifies structured reasoning-acting, contextual memory, and efficient execution. It (i) employs explicit subtask management with tree-structured exploration for controllable multi-branch reasoning, (ii) bootstraps exploration through efficient web state replay with background reasoning, and (iii) leverages a page action memory to share explored actions within and across sessions. On the WebArena benchmark, Branch-and-Browse achieves a task success rate of 35.8% and reduces execution time by up to 40.4% relative to state-of-the-art methods. These results demonstrate that Branch-and-Browse is a reliable and efficient framework for LLM-based web agents.