已审阅并标注「手机操作」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。
Executes instructions from mobile how-to search results inside a controlled Android environment, then uses the observed success of those instructions to verify and rerank technical-support results.
LlamaTouch executes mobile tasks on devices and evaluates whether an agent visits manually annotated essential application or system states. Screenshot and hierarchy annotations, combined with exact and fuzzy state matching, support evaluation of 496 tasks across multiple agents.
Trains a smartphone assistant from sequences of screenshots paired with earlier actions. The model predicts UI-only interactions such as taps and swipes, with evaluation on Android in the Wild.
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 Chain-of-Action-Thought and Android-In-The-Zoo annotations that connect prior actions, screen observations, intended actions, and expected outcomes.
Combines screenshots, layout information, and action history with a factored action predictor for smartphone automation.
Uses visual perception tools and task decomposition to operate mobile applications without relying on app interface metadata.
Introduces GPTVoiceTasker, a mobile assistant that interprets user commands, executes device interactions, and learns from prior commands to streamline later task execution. The work includes a user study of task efficiency.
Combines operating-procedure context with user interaction to guide mobile task automation and handle personalized or sensitive requests.
Executes voice-requested mobile tasks through GUI exploration, backtracking, and accumulated interaction experience.
Builds app knowledge through exploration or human demonstrations and uses it to guide multimodal smartphone interactions.
VisionTasker converts screenshots into textual UI interpretations and presents one interface at a time to an LLM planner for action selection. It evaluates visual representations and execution of 147 tasks on an Android smartphone, including integration with programming by demonstration.
Presents LLMPA, a mobile process-automation architecture that decomposes requests, identifies interface elements, predicts actions and checks errors. Demonstrations evaluate multistep operations in Alipay.
Introduces MobileGPT, which organizes mobile-app experience into reusable subtasks using an explore, select, derive, and recall cycle. Its memory supports learning task procedures and adapting them to new contexts.
Studies MM-Navigator, a multimodal agent that interprets smartphone screenshots and predicts localized actions without task-specific training.
Introduces Auto-GUI, a screenshot-based agent using previous actions and future action plans to guide device interaction.
Combines language-model reasoning with app analysis, UI representations, and exploration-derived memory for Android task automation.
Collects Android interaction demonstrations with screens, actions, and instructions across device and platform variations for robustness evaluation.
Transforms Android UI states and available actions into language prompts for an LLM to choose and execute task steps.
Introduces multilingual smartphone instruction-following data and a pipeline that retrieves help instructions and maps them to UI actions.
Studies few-shot prompting of a single language model for four mobile-UI interaction tasks, aiming to support conversational interface use without a separate trained model for each task.
Introduces GUI-based task-oriented dialogue and a dataset pairing mobile-interface operations with conversational responses.
Introduces MoTIF mobile-app interactions with feasible and infeasible commands, feasibility explanations, and follow-up questions for ambiguous requests.
Introduces PIXELHELP for predicting mobile UI action sequences from instructions, together with action-phrase annotations and synthetic UI action descriptions for training. Separate Transformers extract instruction steps and ground object descriptions using interface content and screen position.
Introduces PUMICE, an agent that learns mobile-app procedures and conditional concepts through natural-language conversation and GUI demonstrations, recursively resolving ambiguous instructions with users.
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.
Introduces APPINITE, a conversational interface for specifying the intended targets of demonstrated Android actions. It constructs semantic UI representations and uses an on-screen overlay to preview and refine executable data descriptions.
Introduces SUGILITE, which combines spoken instructions, demonstrated Android actions, and UI hierarchies to generate reusable automation scripts. Its interface includes context checking and repairs for unfamiliar situations and changing app interfaces.
Reproducible Android benchmark of 138 tasks across nine apps on predefined virtual devices, run via AVD on Mac or Docker on Linux, released with the Android Instruct training set.
A graph-based mobile GUI benchmark that evaluates long tasks through screenshot states and multiple valid or erroneous transitions, including reflection, replanning and backtracking.
A federated mobile-agent training and evaluation suite that varies user-data heterogeneity and application distribution, with released partition annotations and inference/scoring scripts.
A public set of real-device mobile task definitions used to evaluate MobA, with Chinese and English task material packaged in a versioned JSON release.
Offline mobile-agent task data spanning common tasks and released noisy, contaminated and ambiguous-instruction subsets.
Automated benchmark for mobile LLM agents whose default tasks use ten Simple Mobile Tools Android apps, installed as a Python library that detects task completion.
Mobile-app task definitions covering everyday scenarios, with annotated preconditions and clarification requirements for evaluating agent behavior.
A browser-hosted mobile-app simulator with programmable state, parameterized tasks and deterministic state-checking judges for parallel GUI-agent evaluation and online reinforcement learning.
Browser-rendered mobile simulation with resettable app state and a shared task suite for GUI-only and GUI-plus-tool agents.
A containerized Android evaluation environment with GUI-only, agent-user interaction and MCP-augmented tasks, plus checks on application and backend state.
Benchmark of semantic world modeling for mobile agents, with question-answering tasks and GPT-judged generation tasks, plus training data built on AitW and AndroidControl screens.
340 single-app and cross-app tasks over 66 Chinese and English Android apps, with plug-in support for 11 smartphone agents and automatic coarse-to-fine success detection.
Android demonstrations with high-level goals, step instructions, screenshots, and accessibility trees.
Conversation-formatted supervision released for fine-tuning AutoDroid V2, with the project documenting a ShareGPT-style JSON configuration.
Instruction-to-function-call examples for learning Android intent invocation, with training, testing and API-annotation files for mobile task execution.
Cross-app Android interaction episodes with fine-grained step instructions, screen descriptions, action context, and target boxes.
Cross-platform mobile GUI trajectory dataset derived from instructional videos, with released data-processing helpers and example evaluation code for Android and iOS data.
Video-derived mobile navigation annotations that pair scene boundaries and screen or element boxes with action labels for training and evaluating GUI agents.
Mobile-agent supervision from emulator and simulator trajectories, plus executable tasks with starting states and success checks for reinforcement learning.
Reverse-task-synthesis mobile trajectories released in separate AndroidControl and AndroidWorld training annotation files.
Mobile GUI reward annotations released for training UI-Genie’s trajectory-assessment model.
Synthetic mobile GUI trajectory supervision and screenshots released with the UI-Genie agent-training pipeline.
A public example subset of the UI-S1 mobile training data, packaged as JSONL annotations and Parquet images.
8B on-device smartphone agent built on MiniCPM-V that operates Chinese and English apps from screenshots, trained with reinforcement fine-tuning and a compact JSON action space.
An eight-billion-parameter MiniCPM-V-based model that consumes smartphone screenshots and predicts compact actions for Chinese and English Android app tasks.
AutoGLM phone-agent checkpoint for Open-AutoGLM, fine-tuned from GLM-4.1V-9B-Base with about 10.3B BF16 parameters and tagged for Chinese.
Multilingual variant of the AutoGLM phone-agent checkpoint for Open-AutoGLM, likewise fine-tuned from GLM-4.1V-9B-Base with about 10.3B BF16 parameters.
Mobile GUI agent research release with technical report, benchmark data, and evaluation tooling from vivo AI Lab.
第 181–240 条，共 282 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。
