WebCanvas: Benchmarking Web Agents in Online Environments
Introduces WebCanvas and Mind2Web-Live, evaluating online task progress through meaningful intermediate states on changing websites.
网页
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。
CAAP: Context-Aware Action Planning Prompting to Solve Computer Tasks with Front-End UI Only
CAAP converts screenshots into textual observations and plans keyboard-and-mouse actions using a prompt that examines task context from multiple perspectives. The agent is evaluated on MiniWoB++ and WebShop using only front-end visual observations.
网页
WebSuite: Systematically Evaluating Why Web Agents Fail
WebSuite organizes browser operations into an action taxonomy and tests both isolated controls and complete workflows. Its diagnostic tasks attribute failures to specific actions, enabling comparison of text-based and multimodal web agents.
网页
Large Language Models Can Self-Improve At Web Agent Tasks
Examines self-improvement by fine-tuning web agents on three mixtures of model-generated training data. WebArena experiments and trajectory-level evaluation measures study task performance, robustness, and behavior beyond aggregate success rates.
网页
Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning
Combines supervised and reinforcement learning for MiniWoB web tasks and investigates whether agents understand HTML structure or memorize target elements.
网页
Grounded Language Agent for Product Search via Intelligent Web Interactions
Introduces GLAINTEL, a Flan-T5-based product-search web agent studied under unsupervised learning, demonstration-based training, and unsupervised domain adaptation. It compares ways to combine demonstrations with reinforcement learning.
网页
WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents
WILBUR learns to rank prior task demonstrations for a web agent’s prompt and synthesizes instructions from past runs. A generated task curriculum and a backtracking mechanism support adaptation and recovery, evaluated on WebVoyager.
网页
AutoWebGLM: A Large Language Model-based Web Navigating Agent
Builds a web agent through simplified HTML observations, human-and-AI browsing data, curriculum training, and reinforcement-learning refinement.
网页
Tur[k]ingBench: A Challenge Benchmark for Web Agents
Evaluates web agents on multimodal annotation tasks adapted from HTML interfaces originally built for crowdsourcing workers.
网页
WIPI: A New Web Threat for LLM-Driven Web Agents
Studies WIPI, a black-box indirect-instruction threat in which webpage content redirects LLM-driven web agents. Evaluation spans plugin-based agents, Web GPTs, and open-source web-agent implementations.
网页
On the Multi-turn Instruction Following for Conversational Web Agents
MT-Mind2Web evaluates web navigation through sequences of conversational user instructions. Self-MAP combines memory-augmented planning with reflection to preserve context and dependencies across those interaction turns.
网页
WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
Collects expert demonstrations of conversational web navigation and studies retrieval-based element selection for processing large pages.
网页
Dual-View Visual Contextualization for Web Navigation
Uses screenshot geometry and visual content to enrich HTML element representations for web navigation. Nearby elements contribute textual and visual context, with evaluation on cross-task, cross-website, and cross-domain Mind2Web splits.
网页
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
Combines multimodal web interaction with a real-website task collection and an automated evaluation protocol.
网页
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
Introduces visually grounded website tasks for evaluating multimodal agents that must interpret both images and text.
网页
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Introduces AgentBoard, a multiturn agent evaluation framework with intermediate progress metrics and analysis tools. Its broader task suite includes WebShop and WebArena interactions with stepwise progress measurements.
网页相关研究
GPT-4V(ision) is a Generalist Web Agent, if Grounded
Introduces SeeAct and live-website evaluation, examining how visual planning and element grounding affect web-agent task completion.
网页
WebVLN: Vision-and-Language Navigation on Websites
WebVLN trains website navigation from question-based instructions using both rendered visual information and underlying HTML. It introduces WebVLN-v1 and a website-aware navigation network to study this digital variant of vision-and-language navigation.
网页
Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
CompWoB adds 50 composed web-automation tasks to study generalization from simpler interactions. The paper compares prompted and fine-tuned agents, balances task training data, and probes sensitivity to changes in instruction order.
网页
WebWISE: Web Interface Control and Sequential Exploration with Large Language Models
WebWISE filters DOM elements into observations and generates short programs for click, scroll, and text-entry steps. It evaluates in-context learning from either one supplied example or an example collected during a successful zero-shot MiniWoB++ trial.
网页
AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models
AllTogether standardizes prompts for HTML-based web navigation and compares prompting with instruction fine-tuning. Its analysis examines how HTML context, interaction history, and current environmental feedback affect task execution.
网页
OpenAgents: An Open Platform for Language Agents in the Wild
OpenAgents hosts three language agents, for data analysis, API plugins and autonomous web browsing, behind a web interface for non-expert users, with local deployment for developers.
网页相关研究
A Zero-Shot Language Agent for Computer Control with Structured Reflection
Studies a zero-shot computer-control agent that plans executable actions and organizes its own reflections after mistakes. MiniWoB++ experiments examine learning to complete tasks without supplied expert trajectories.
网页
SteP: Stacked LLM Policies for Web Actions
SteP dynamically composes specialized web-action policies through a stack that records the active chain of policy calls. It studies this control structure across WebArena, MiniWoB++, and CRM workflows.
网页
LASER: LLM Agent with State-Space Exploration for Web Navigation
LASER represents web navigation as exploration over a defined set of states, allowing an agent to revisit earlier states after mistakes. The study evaluates this backtracking approach on WebShop and Amazon tasks.
网页
WebArena: A Realistic Web Environment for Building Autonomous Agents
Introduces reproducible web environments with task-completion checks for evaluating autonomous web agents.
网页
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Combines task decomposition, HTML summarization, and generated Python programs to carry out instructions on websites.
网页
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
Synapse filters task-irrelevant page state and places complete abstracted state-action trajectories into the prompt. An embedding-based exemplar memory retrieves relevant demonstrations for new tasks, evaluated on MiniWoB++ and Mind2Web.
网页
Mind2Web: Towards a Generalist Agent for the Web
Introduces a web-task dataset spanning diverse websites and evaluates generalization to unseen sites and domains.
网页
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Studies instruction-following agents that observe screenshots and act through a generic mouse-and-keyboard action space, evaluating pixel-based pretraining for GUI tasks on MiniWoB++.
网页
Hierarchical Prompting Assists Large Language Model on Web Navigation
Separates web navigation prompting into a SUMMARIZER that extracts action-relevant observations and an ACTOR that chooses the next action from the condensed context.
网页
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Trains WebGUM offline from demonstrations by jointly tuning an instruction-following language model and a vision encoder over webpage screenshots and HTML. The agent predicts browser actions and is evaluated on MiniWoB, WebShop, and Mind2Web.
网页
Language Models can Solve Computer Tasks
Introduces recursive criticism and improvement prompting for language-model agents performing computer tasks, evaluated on MiniWoB++ with a small number of demonstrations per task.
网页
Understanding HTML with Large Language Models
Studies language models for HTML element classification, page description and autonomous web navigation. Fine-tuned models are evaluated on MiniWoB, and a distilled, automatically labeled CommonCrawl HTML corpus supports the training approach.
网页
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Provides a simulated shopping environment where language agents search, configure, and select products from natural-language requirements.
网页
Grounding Open-Domain Instructions to Automate Web Support Tasks
Introduces RUSS, which translates support instructions into a domain-specific language and grounds them in actionable web elements.
网页
Rousillon: Scraping Distributed Hierarchical Web Data
Introduces Rousillon, which generalizes a demonstration of collecting one hierarchical data row into a browser-automation program that traverses related pages. The paper develops relation-selection and generalization methods and evaluates users building such scripts.
网页
World of Bits: An Open-Domain Platform for Web-Based Agents
Introduces World of Bits, a web-task platform combining human demonstrations, keyboard and mouse actions, and cached HTTP traffic for repeatable task environments. It evaluates agents trained through behavioral cloning and reinforcement learning.
网页
Ringer: Web Automation by Demonstration
Introduces Ringer, which converts demonstrated webpage interactions into scripts combining actions, target selectors, and waiting conditions. It evaluates replay robustness on tasks recorded from real websites.
网页
End-to-End Goal-Driven Web Navigation
Introduces WebNav for converting websites into goal-directed hyperlink navigation tasks and WikiNav for evaluating language-conditioned navigation and question answering on Wikipedia.
网页
Koala: Capture, Share, Automate, Personalize Business Processes on the Web
Introduces Koala, a collaborative web automation system that records browser interactions as editable pseudo-natural-language scripts. Scripts are shared through a wiki and instantiated with personal or corporate data for reuse by other users.
网页
PLOW: A Collaborative Task Learning Agent
Describes PLOW, which learns executable web-task models from a session combining demonstrations, natural-language explanations, and dialogue. Browser instrumentation connects user actions with DOM structure to support task generalization.
网页
AgentRewardBench
A benchmark and evaluation toolkit for comparing automatic web-agent judges against expert judgments of task success, side effects and repetition.
网页
BrowserART
Red-teaming benchmark and test suite from Scale AI evaluating whether refusal-trained language models can be jailbroken when deployed as browser agents.
网页
CUAVerifierBench
Human-annotated browser-agent trajectories for comparing automated task-success and process-quality verifiers against reviewer judgments.
网页
EIA
Evaluation suite for Environmental Injection Attacks that embed invisible malicious HTML elements into benign websites to test privacy leakage in generalist web agents.
网页
Mind2Web 2
Long-horizon agentic web search benchmark whose Agent-as-a-Judge framework scores time-varying, citation-backed answers, with evaluation scripts for its dev and test sets.
网页
Online Mind2Web
300 tasks on 136 live websites for evaluating web agents online, with outdated tasks replaced over time, human-reviewed submissions and the WebJudge automatic evaluator.
网页
ST-WebAgentBench
BrowserGym-based benchmark for evaluating the safety and policy compliance of enterprise web agents across six trustworthiness risk dimensions.
网页
WebClick
A web-interface localization benchmark with screenshot instructions and target boxes, including agent browsing, human browsing and calendar cases.
网页
WebGuard
Codebase, annotation toolkit, and action-level risk dataset for training and evaluating guardrail models that flag unsafe browser-agent actions before execution.
网页
WebRewardBench
An offline preference-evaluation set for web process reward models, pairing page and trajectory context with preferred and rejected candidate decisions.
网页
WebTailBench
Live-web task definitions and rubrics for evaluating computer-use agents, with preserved original tasks, a refreshed V2 task suite and a separate refusal set.
网页
WebTestBench
An end-to-end web-testing benchmark where agents derive test checklists from development instructions, interact with deployed applications and report functional or constraint-related defects.
网页
Go-Browse-WA processed data
Flattened web-interaction training records with accessibility-tree observations, assistant completions, trajectory rewards and step-link metadata.
网页
第 181–240 条，共 306 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。