Cradle
Framework in which foundation models control games and software from screenshots alone, acting through keyboard and mouse, shown on RDR2, Stardew Valley, Cities: Skylines and Dealer's Life 2.
桌面
规划
已审阅并标注「规划」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。
D-PoT evaluation code
Offline prompting and evaluation code for Dynamic Planning of Thoughts on Android-in-the-Wild, including action extraction and comparison with reference actions.
Android
GUI-CIDER research code
Released data-synthesis and evaluation scripts that distill planning and causal GUI knowledge into text for mid-training mobile interface agents.
Android
GUI-ReWalk
A desktop trajectory-generation framework that moves from stochastic GUI exploration to inferred goals and multi-stage task completion, with retrospective reasoning annotations.
桌面Linux
GUIPivot
Query-inference training tools connecting screenshot grounding with GUI action reasoning, including preprocessing, query refinement and offline single-step evaluation on AndroidControl and AITZ.
Android
LiteWebAgent
Modular web-agent framework with browser control, planning, workflow memory, and tree-search components, plus web and extension interfaces.
网页
MobA
An Android agent that combines global task planning and memory with a local action executor, using reflection to revise mobile interaction steps.
Android
Mobile-Agent-E code component
Android automation component with hierarchical planning, reflection and persistent tips/shortcuts learned across task sequences.
Android
MobileGPT
An Android client and Python-server agent that learns reusable app subtasks through exploration, selection, derivation and memory recall.
Android
Mobilerun (formerly Droidrun)
A framework that combines screenshots and accessibility state with agent tools for mobile-device tasks through command-line and Python interfaces.
AndroidiOS
OS-Copilot
Open-source library for generalist agents acting on an operating system's web, terminals, files and third-party apps, with the FRIDAY assistant, which takes custom tools and self-learns Excel tasks.
桌面
PC-Agent
Human-cognition-transfer framework for PC agents: PC Tracker logs human computer use, cognition completion turns logs into cognitive trajectories, and a planner works with a grounding agent.
桌面
PC-Agent (X-PLUG component)
Multi-agent desktop automation component for Windows and macOS, combining active perception, task decomposition and reflection for workflows spanning applications.
桌面WindowsmacOS
Plan-and-Act
A web-agent framework that separates high-level planning from action execution, with replanning and synthetic planner-data generation components.
网页
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.
网页
ScreenAgent
Environment and agent in which a vision-language model controls real desktops over VNC with mouse and keyboard in plan, act and reflect stages, plus a hand-annotated dataset of daily computer tasks.
桌面
Self-MAP
A conversational web-agent implementation with candidate ranking and memory-assisted action planning, including optional memory simplification, refinement and self-reflection modules.
网页
StateAct
State-tracking prompts and experiment runners for language agents, including a WebShop implementation alongside text-based environments.
网页相关研究
Synapse
A computer-control research implementation that retrieves example trajectories from memory, abstracts task-relevant state and prompts an agent to navigate browser tasks.
网页
VisionTasker
An Android automation implementation that translates screenshot-based UI understanding into language descriptions for step-by-step LLM planning and action execution.
Android
WebDreamer
World-model and planning components that simulate web-action outcomes, with linked training data and model checkpoints.
网页
WorkForceAgent-R1
Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.
网页
Building AI Browser Agents
Browser-agent course with worked lessons on structured web extraction and multi-step browser interaction, followed by AgentQ search and self-correction concepts.
网页
第 301–325 条，共 325 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。