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.
Desktop
Planning
Source-reviewed research and assets tagged with Planning.
Membership follows reviewed tags; it does not establish a dependency between neighboring records. Dates preserve source precision. Annotations retain their original language.
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.
DesktopLinux
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.
Web
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.
Desktop
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.
Desktop
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.
DesktopWindowsmacOS
Plan-and-Act
A web-agent framework that separates high-level planning from action execution, with replanning and synthetic planner-data generation components.
Web
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.
Web
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.
Desktop
Self-MAP
A conversational web-agent implementation with candidate ranking and memory-assisted action planning, including optional memory simplification, refinement and self-reflection modules.
Web
StateAct
State-tracking prompts and experiment runners for language agents, including a WebShop implementation alongside text-based environments.
WebAdjacent research
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
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.
Web
WorkForceAgent-R1
Web-task reward functions, WorkArena data processing and GRPO training configurations for reasoning-oriented language agents.
Web
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.
Web
Showing 301–325 of 325 resources.
Get full records and evidence through the topic export manifest. Source records can be passed to the standard RAG and citation exporters after cloning the catalog.