MT-Mind2Web
Multi-turn web-navigation conversations constructed from Mind2Web interactions, with dialogue turns, HTML snapshots, element candidates and click/type/select action sequences.
网页
模仿学习
已审阅并标注「模仿学习」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。
OS-Genesis mobile training data
Reverse-task-synthesis mobile trajectories released in separate AndroidControl and AndroidWorld training annotation files.
Android
PC-Agent-E training data
Released dataset used to train PC-Agent-E, linked by the official pipeline for refining human trajectories and synthesizing action reasoning.
桌面WindowsLinux
ShowUI-π training data
Drag-and-click episode data for the ShowUI-π model, spanning desktop editing, presentation, handwriting and other interface tasks.
桌面
UI-Genie trajectory data
Synthetic mobile GUI trajectory supervision and screenshots released with the UI-Genie agent-training pipeline.
Android
VideoCAD data
CAD screen recordings paired with action logs and target model images for studying precise interface control and long-horizon visual imitation.
网页
WebEvolver SFT data
Two JSONL collections for supervised fine-tuning the WebEvolver agent policy and web world model.
网页
Go-Browse WebArena Qwen 7B
A Qwen-2.5-7B-Instruct checkpoint fine-tuned on Go-Browse WebArena trajectories for website task execution.
网页
Llama-3-8B-Web
A Llama 3 8B instruction-model checkpoint fine-tuned on WebLINX web interactions and dialogue, predicting browser actions from a textual state representation.
网页
OS-Genesis 7B AC
The AndroidControl-oriented Qwen2-VL checkpoint trained with mobile trajectories generated through OS-Genesis reverse task synthesis.
Android
PC-Agent-E checkpoint
Computer-use checkpoint fine-tuned on PC-Agent-E trajectories; the model-card prose identifies Qwen2.5-VL-72B-Instruct as its starting model.
桌面WindowsLinux
UI-Genie Agent 7B
A Qwen2.5-VL mobile action model trained using existing and reward-guided synthetic trajectories from the UI-Genie framework.
Android
Go-Browse
Structured website-exploration and data-processing code that revisits discovered pages, proposes tasks and collects trajectories for web-agent fine-tuning.
网页
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
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
LearnAct
Released inference and evaluation code for demonstration-conditioned mobile GUI agents on LearnGUI-Offline. The repository describes a multi-agent adaptation method and links the LearnGUI demonstrations.
MemGUI-Agent
MemGUI-Agent training and offline evaluation tools provide trajectory conversion, LoRA SFT templates, and step-level checks of GUI actions, memory updates and context folding.
Android
PC-Agent-E training and deployment
Tools for refining and augmenting human computer-use trajectories, preparing supervised training data, and deploying a native PC-Agent-E scaffold.
桌面WindowsLinux
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
TongUI training and inference framework
Training configurations, preprocessing and inference examples for tutorial-trained GUI models, with a LLaMA-Factory fine-tuning workflow and screenshot-grounding interfaces.
跨平台桌面网页
UI-Genie
Training and evaluation code for a mobile-agent framework that iteratively generates trajectories using agent and reward-model feedback.
Android
VideoCAD training and evaluation code
VideoCADFormer training, action-log preprocessing and evaluation code for learning CAD interface action sequences from screen recordings of browser-based Onshape.
网页
WebLlama
Training, evaluation and integration tooling for dialogue-guided web agents, including Llama fine-tuning workflows and BrowserGym examples built around WebLINX.
网页
WinDOM code
GUI-grounding training and evaluation code with same-family distillation, GRPO recipes and point-in-box scoring, using a Windows-style web environment.
网页
第 61–84 条，共 84 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。