网页导航
已审阅并标注「网页导航」的研究与资产。
条目依据已审阅标签归类，同一主题不表示资源之间存在依赖关系。日期保留来源精度，注释保留原语言。
Go-Browse-WA processed data
Flattened web-interaction training records with accessibility-tree observations, assistant completions, trajectory rewards and step-link metadata.
MT-Mind2Web
Multi-turn web-navigation conversations constructed from Mind2Web interactions, with dialogue turns, HTML snapshots, element candidates and click/type/select action sequences.
NNetNav Live data
Browser-interaction data released with NNetNav for its live-website setting, with separate training and test files.
NNetNav WebArena data
NNetNav's WebArena-oriented browser-interaction data release, with separate training and test files.
Plan-and-Act training data
Planner and action-executor training examples for WebArena-Lite and WebVoyager, with model-specific processed files and raw trajectory annotations.
WebEvolver SFT data
Two JSONL collections for supervised fine-tuning the WebEvolver agent policy and web world model.
WebPRM checklist-generation data
Web-task context, starting observations and action history paired with structured checklists and subgoal analyses for checklist generation.
WebPRM Collection preference data
Checklist-annotated web decision records with page observations, prior actions, one preferred continuation and rejected alternatives for process-reward learning.
Fara
Microsoft browser-use agent models that act from screenshots by predicting click coordinates without accessibility trees; Fara1.5 comes in 4B, 9B and 27B, succeeding Fara-7B.
Fara 7B
Microsoft's Fara checkpoint, a Qwen2.5-VL-architecture image-text-to-text model with about 8.3B BF16 parameters, English, MIT-licensed and linked to arXiv paper 2511.19663.
Go-Browse WebArena Qwen 7B
A Qwen-2.5-7B-Instruct checkpoint fine-tuned on Go-Browse WebArena trajectories for website task execution.
Holo1 7B
A Qwen2.5-VL-based action model released for the Surfer-H web-agent system, supporting policy, interface-localization and validation roles.
Llama-3-8B-Web
A Llama 3 8B instruction-model checkpoint fine-tuned on WebLINX web interactions and dialogue, predicting browser actions from a textual state representation.
PAE LLaVA 7B
A released LLaVA checkpoint for visual browser interaction from the PAE autonomous task-proposal and policy-learning system.
Plan-and-Act Planner 70B
The planner component of Plan-and-Act, generating structured high-level plans that an executor turns into web actions.
WebJudge 7B
A visual trajectory judge that retains selected intermediate screenshots to evaluate whether a web agent completed its task.
WebRL Llama 3.1 8B
A WebRL browser-policy checkpoint for performing actions in the five website environments of WebArena.
WebRL outcome reward model 8B
The outcome-supervision checkpoint used by WebRL to score browser trajectories during policy training.
WebShepherd 3B
A public text-based process-reward checkpoint from the Web-Shepherd collection for scoring web-agent decisions against task checklists.
Agent E
Browser automation agent on the AG2 framework that pairs a planner agent with a browser navigation agent to fill forms, search shops and work through sites, also callable over a local HTTP API.
Agent Workflow Memory implementation
Research code that extracts reusable browser-task routines from demonstrations or prior executions, stores them as workflow memory and reuses them during subsequent navigation.
agent-browser
A browser-automation command-line interface that exposes browser state and interaction commands for AI agents.
Agent-R
Trajectory collection and revision utilities that use tree search and model-guided critique to train agents to recover from mistakes, including WebShop tasks.
Amazon Nova Act
AWS service for building and deploying agents that automate browser-based UI workflows from natural language and Python, powered by a custom Nova 2 Lite model.
AutoWebGLM
Web navigation agent built on ChatGLM3-6B that simplifies HTML for the model, is trained on hybrid human and AI data with RL and rejection sampling, and comes with the bilingual AutoWebBench.
Browser Use
Open-source browser agent library that runs locally with any LLM against a local or cloud browser, and also serves as a CLI for coding agents and as a driver for Claude's browser toolset.
Browser Use WebUI
A Gradio interface for configuring and running Browser Use agents, including persistent browser sessions and interaction recordings.
BrowserOS / BrowserOS neo
Chromium-based browser implementations for external agent control and built-in assistant workflows, with session visibility and replay facilities.
CAAP Agent
Screenshot-driven agent implementation for MiniWoB++ and WebShop, using a visual observer and context-aware prompts to issue mouse and keyboard actions.
Go-Browse
Structured website-exploration and data-processing code that revisits discovered pages, proposes tasks and collects trajectories for web-agent fine-tuning.
HyperAgent
Library adding natural-language commands to Playwright: accessibility-tree single actions, multi-step tasks that can use screenshots, an MCP client and action caching for replay without LLM calls.
LaVague
Open-source web agent framework where a World Model turns an objective and the current page into instructions and an Action Engine compiles them into Selenium or Playwright code to run.
LiteWebAgent
Modular web-agent framework with browser control, planning, workflow memory, and tree-search components, plus web and extension interfaces.
Lumen browser agent
A screenshot-driven browser agent over Chrome DevTools Protocol, with resumable sessions, context compression, action replay and configurable completion checks.
Nanobrowser
A browser-extension agent that reads pages, interacts with elements and moves between tabs from a side-panel task interface.
NNetNav
Collects and labels browser-exploration trajectories for agent training, with code for data processing, fine-tuning, and web evaluation.
Notte
Web agent framework and cloud SDKs for managed Chrome sessions, adding a CLI, an MCP server for coding agents, serverless browser functions and an API that builds automations from English tasks.
OpenAgents Web Agent
The OpenAgents browser-control component, connecting a Chrome extension to a web agent and local chat platform for navigating sites and completing interface tasks.
ORBIT framework
Inspect-based multi-agent evaluation framework with role, scheduling and communication controls, BrowserART accessibility-tree actions, and desktop mouse, keyboard and screenshot tools.
Plan-and-Act
A web-agent framework that separates high-level planning from action execution, with replanning and synthetic planner-data generation components.
Proposer-Agent-Evaluator (PAE)
A browser-agent training system that proposes tasks, collects visual interaction trajectories, and uses automated evaluation to drive policy improvement.
RCI Agent
A MiniWoB++ agent that uses explicit and implicit recursive criticism-and-improvement prompts to refine action plans and ground actions to browser state.
SeeAct
Generalist web agent framework for large multimodal models such as GPT-4V, with a Playwright tool that runs agents on live websites, text-choice and set-of-mark grounding, and a crawler mode.
Self-MAP
A conversational web-agent implementation with candidate ranking and memory-assisted action planning, including optional memory simplification, refinement and self-reflection modules.
SkillWeaver
A web-agent framework that explores sites, synthesizes reusable interaction APIs and builds a skill library for later tasks.
StateAct
State-tracking prompts and experiment runners for language agents, including a WebShop implementation alongside text-based environments.
Steel Browser
Open-source browser API managing Chrome sessions for agents, reachable through Puppeteer, Playwright or Selenium over CDP, with persisted cookies, proxy rotation, stealth and a session debugging UI.
Surf New
Next.js and FastAPI playground from Steel for trying web agents in a controlled browser environment, with live views of browser interaction and support for providers such as Claude and GPT-4.
Synapse
A computer-control research implementation that retrieves example trajectories from memory, abstracts task-relevant state and prompts an agent to navigate browser tasks.
Web-Shepherd inference and evaluation
Process-reward inference and benchmark-evaluation utilities that use task checklists to assess individual web-agent decisions.
WebAgent-R1
Environment setup, multi-turn reinforcement-learning and evaluation tooling for browser agents interacting with WebArena.
第 241–300 条，共 308 条资源。
通过主题导出清单获取完整记录和证据。克隆目录后，可将主题记录直接交给标准 RAG 与引用导出工具。