已审阅并标注「工作流」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。
BIMgent plans software-specific workflows and executes GUI actions for building-information modeling. It evaluates multimodal building design and reconstruction tasks in professional authoring software.
macOSWorld provides 202 interactive tasks across 30 applications, with instructions and operating-system interfaces in five languages. It evaluates GUI agents on macOS workflows and includes a separate subset for deception-attack testing.
Uses rule-based rewards for output structure and action correctness to train reasoning for enterprise web navigation.
ScienceBoard combines an interactive environment with professional scientific software and 169 human-curated tasks in areas including biochemistry, astronomy, and geoinformatics. It evaluates computer-use agents on visually rich research workflows and analyzes their execution limitations.
Describes the CUGA enterprise-agent development process, emphasizing iterative evaluation, failure analysis, and refinement on software-task benchmarks.
Simulates a software-company workplace to evaluate agents on professional tasks involving websites, programs, files, and coworker communication.
Studies fine-tuning open language models on production web-workflow traces, including training choices for specialized web agents.
Agent Workflow Memory extracts reusable task routines and selectively supplies them to guide later web actions. It studies both offline workflow induction from training examples and online induction from test experience on Mind2Web and WebArena.
IDA helps business users create web UI automation through guided demonstrations, a semantic programming model, and a teaching-oriented interface. A prototype user study examines automation creation with enterprise applications by users without programming backgrounds.
Benchmarks multimodal agents on data-science and engineering workflows involving enterprise applications, code, and GUI operations in real computer environments.
Defines compositional enterprise workflows to evaluate planning and reasoning, with generation of ground-truth interaction traces.
Introduces WONDERBREAD, a benchmark pairing human WebArena workflow demonstrations with screen recordings, action logs, and written procedures. Six evaluation tasks cover documentation, knowledge transfer, and process improvement beyond end-to-end execution.
Presents SmartFlow, which converts visible GUI elements into text for language-model action planning and executes the plan through a scripting engine. A collection of enterprise applications evaluates adaptation to different layouts and tasks.
Prompt2Task converts textual goals or procedures into smartphone UI automation using agents for intent interpretation, external-information handling, and execution. User feedback and accumulated task knowledge support subsequent task generation and operation.
Introduces enterprise web tasks on ServiceNow and BrowserGym interfaces for evaluating browser-based agents.
Benchmarks robustness of API-based PowerPoint completion under sentence-level, semantic, and multilingual instruction perturbations and changes to the available API set.
Combines operating-procedure context with user interaction to guide mobile task automation and handle personalized or sensitive requests.
Introduces InstructExcel, a benchmark for generating Excel OfficeScripts from natural-language requests, built using scripts recorded from user actions and a collection of existing spreadsheets.
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.
Introduces SheetCopilot, an agent that steers spreadsheet software via atomic virtual APIs, along with a 221-task spreadsheet manipulation benchmark.
Derives task graphs from demonstrated Android app interactions and layers a conversational question-answer interface over those graphs. The evaluation examines task-model extraction and developer use of the resulting bot templates.
Uses workflows extracted from demonstrations to constrain reinforcement-learning exploration for interactive web tasks.
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.
Human reference trajectories and scoring code for measuring the action efficiency of computer-use agents on OSWorld tasks.
106 browser-driven business workflows across 23 self-hosted SaaS apps in six domains, scored by per-task verifiers that read each app's database and give partial credit.
Self-contained workplace environment for evaluating agents on professional tasks involving websites, files, code, and simulated coworkers.
An offline benchmark of workflow documentation, quality assessment and knowledge transfer using human web-navigation demonstrations, action traces and written procedures.
Archives of ScienceBoard agent evaluation runs, separated by agent configuration and screenshot, accessibility-tree or set-of-marks observation mode.
Desktop demonstrations with task descriptions, videos, input logs, and action-linked screenshot evidence for studying reusable agent skills.
Research code that extracts reusable browser-task routines from demonstrations or prior executions, stores them as workflow memory and reuses them during subsequent navigation.
Agentic test-automation platform running plain-language test cases from pixels rather than selectors on desktop apps, Citrix, in-car head units and mobile devices, deployable on-premise or air-gapped.
Open-source desktop agent that works inside its own Ubuntu Linux virtual desktop, with a web task interface, REST APIs for tasks and direct control, a takeover mode and password-manager logins.
Mobile automation framework that uses reusable basis subtasks to constrain and refine planning between user goals and executable actions.
Gradio desktop GUI agent for Windows and macOS that needs no Docker, using Claude 3.5 Computer Use over the API or ShowUI and UI-TARS run locally, with multi-display and phone remote control.
Monorepo behind Cua Spaces, which gives agents full macOS or Linux desktops, plus Cua Driver for operating native apps, Lume for Apple Silicon VMs, Cua Bench and the CUA-S1 decision models.
Mobile-control research implementation combining operating-procedure context with human interaction for personalized task execution.
An Android client and Python-server agent that learns reusable app subtasks through exploration, selection, derivation and memory recall.
Spreadsheet automation agent for Windows/Excel, with benchmark assets and a separately released headless Ubuntu evaluation backend.
Desktop agent that records demonstrations, derives semantic action traces, and uses them to plan and execute related workflows.
Browser workflow automation that relies on vision LLMs and a swarm of agents instead of fixed XPath selectors, offered as a Playwright-compatible SDK and a no-code workflow builder.
Hosted Skyvern service for AI browser workflows such as invoice downloads and form filling, with built-in CAPTCHA and 2FA handling, proxy geotargeting, run explanations and JSON or CSV output.
Python toolkit and CLI for building, publishing and running multimodal agents that operate devices such as Ubuntu desktops, locally or on Kubernetes, with task trackers and an agent hub.
Desktop app for a local GUI agent driven by UI-TARS and Seed-1.5-VL/1.6 models, offering local and remote operators for computers and browsers; the repository also ships the Agent TARS CLI and web UI.
Collects human GUI demonstrations and inspects multimodal evidence to derive reusable agent workflow skills.
Research code that learns browser-control policies by constraining exploration with workflows induced from demonstrations, with a Selenium-based MiniWoB environment and experiment harness.
第 61–113 条，共 113 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。
