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。
Applies best-first search to agent actions within interactive web environments, allowing exploration and multistep planning at inference time. WebArena and VisualWebArena experiments examine search behavior and test-time computation.
Introduces WebCanvas and Mind2Web-Live, evaluating online task progress through meaningful intermediate states on changing websites.
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.
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.
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.
Combines supervised and reinforcement learning for MiniWoB web tasks and investigates whether agents understand HTML structure or memorize target elements.
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.
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.
Builds a web agent through simplified HTML observations, human-and-AI browsing data, curriculum training, and reinforcement-learning refinement.
Evaluates web agents on multimodal annotation tasks adapted from HTML interfaces originally built for crowdsourcing workers.
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.
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.
Collects expert demonstrations of conversational web navigation and studies retrieval-based element selection for processing large pages.
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.
Combines multimodal web interaction with a real-website task collection and an automated evaluation protocol.
Introduces visually grounded website tasks for evaluating multimodal agents that must interpret both images and text.
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.
Introduces SeeAct and live-website evaluation, examining how visual planning and element grounding affect web-agent task completion.
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.
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.
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.
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.
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.
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.
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.
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.
Introduces reproducible web environments with task-completion checks for evaluating autonomous web agents.
Combines task decomposition, HTML summarization, and generated Python programs to carry out instructions on websites.
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.
Introduces a web-task dataset spanning diverse websites and evaluates generalization to unseen sites and domains.
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++.
Separates web navigation prompting into a SUMMARIZER that extracts action-relevant observations and an ACTOR that chooses the next action from the condensed context.
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.
Introduces recursive criticism and improvement prompting for language-model agents performing computer tasks, evaluated on MiniWoB++ with a small number of demonstrations per task.
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.
Provides a simulated shopping environment where language agents search, configure, and select products from natural-language requirements.
Introduces RUSS, which translates support instructions into a domain-specific language and grounds them in actionable web elements.
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.
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.
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.
Introduces WebNav for converting websites into goal-directed hyperlink navigation tasks and WikiNav for evaluating language-conditioned navigation and question answering on Wikipedia.
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.
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.
A benchmark and evaluation toolkit for comparing automatic web-agent judges against expert judgments of task success, side effects and repetition.
Red-teaming benchmark and test suite from Scale AI evaluating whether refusal-trained language models can be jailbroken when deployed as browser agents.
Everyday-task benchmark on live websites that runs browser agents in containerized Chromium, blocks each final submission request for scoring by URL match and an LLM judge, and records five layers of run evidence.
Human-annotated browser-agent trajectories for comparing automated task-success and process-quality verifiers against reviewer judgments.
Evaluation suite for Environmental Injection Attacks that embed invisible malicious HTML elements into benign websites to test privacy leakage in generalist web agents.
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.
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.
BrowserGym-based benchmark for evaluating the safety and policy compliance of enterprise web agents across six trustworthiness risk dimensions.
A web-interface localization benchmark with screenshot instructions and target boxes, including agent browsing, human browsing and calendar cases.
Codebase, annotation toolkit, and action-level risk dataset for training and evaluating guardrail models that flag unsafe browser-agent actions before execution.
An offline preference-evaluation set for web process reward models, pairing page and trajectory context with preferred and rejected candidate decisions.
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.
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.
第 181–240 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。
