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。
LineRetriever uses a language model to select observation lines that matter for upcoming web-navigation actions. It reduces DOM or accessibility-tree context by considering the planning horizon instead of relying solely on semantic similarity.
CogniGUI combines hierarchical visual parsing of interface elements with a GRPO-based grounding agent that compares alternative interaction paths. Its ScreenSeek benchmark evaluates navigation across applications, changing interface states, and consistency between interfaces.
Introduces environments that couple 3D physical-world simulations with functional web interfaces. The accompanying benchmark evaluates tasks requiring agents to coordinate online information and physical actions across cooking, navigation and shopping scenarios.
Mirage-1 organizes interaction trajectories into execution, core, and meta-skills, then uses them to guide Monte Carlo tree search during online GUI tasks. It introduces AndroidLH for long-horizon evaluation and tests the approach on Android and web-navigation benchmarks.
UI-NEXUS evaluates compositional mobile tasks in local utility apps and online Chinese and English service apps. AGENT-NEXUS decomposes those long tasks into self-contained atomic subtasks to study generalization beyond isolated screens or short action chains.
Introduces EconWebArena, a curated benchmark of economic-data tasks requiring live website navigation, multimodal interpretation, and precise extraction. It evaluates visual grounding, planning, and interaction design within multistep workflows.
Test-Time Interaction scales the interaction horizon so web agents can explore, backtrack and revise plans within a rollout. Its online reinforcement-learning curriculum adjusts rollout lengths and is evaluated on WebVoyager and WebArena.
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.
ScenGen organizes mobile GUI testing around business scenarios rather than unrestricted exploration. Five collaborating agents observe the interface, choose and execute actions, check scenario completion, and record operations and runtime bugs.
Uses a pre-execution critic and reinforcement training to evaluate proposed GUI actions and provide corrective suggestions before execution.
Models mobile application execution as a finite-state machine to support planning, verification, and recovery across interface transitions.
BacktrackAgent adds verification, judgment, and reflection modules to detect erroneous GUI actions and guide recovery. It develops backtracking-oriented training data that includes post-action pages and evaluates task completion and step accuracy on Mobile3M and Auto-UI.
WebCoT turns reflection, look-ahead, branching and rollback procedures into chain-of-thought training rationales. Fine-tuning on these reconstructed trajectories is evaluated for web-agent self-improvement and transfer across navigation tasks.
GUI-explorer generates exploration goals from screenshots and interface structure, then mines observation-action-outcome triples for app-specific transition knowledge. The resulting training-free agent uses this knowledge during mobile task execution, evaluated on SPA-Bench and AndroidWorld.
FPWC builds and refines a task-oriented world model before planning mobile-device actions. It executes plans as code and evaluates the approach in simulated environments and on real mobile devices.
SPlanner models mobile-app functions and configurations with extended finite-state machines, traverses them to construct execution paths, and converts those paths into natural-language plans. A VLM follows these plans to perform GUI actions, with evaluation on AndroidWorld.
MobileIPL samples trees of action-planning thoughts, propagates rule-based leaf rewards backward, and forms preference pairs for reasoning-level optimization. It also expands screenshot-based instruction data through staged evolution before evaluation on mobile GUI-agent benchmarks.
EcoAgent splits mobile automation between cloud planning and on-device observation and verification. Compact screen descriptions and feedback reduce communication costs, with evaluation on AndroidWorld.
ScaleTrack combines a unified collection of GUI grounding samples with a planning objective that predicts the next action while reconstructing prior actions. This backward prediction links the current screenshot to interaction history during agent training.
Combines iterative web search and link-following with interleaved reasoning and report drafting for deep research. Its reported web explorer retrieves page content through a crawler rather than controlling a visual browser interface.
WebEvolver trains a co-evolving world model to predict web observations and generate additional agent-training trajectories. The same model supports look-ahead action selection at inference, with evaluation on live web-task benchmarks.
Uses a staged reasoning-focused training framework to move GUI agents from reactive actions toward deliberative planning and recovery.
WebRollback gives a web agent an explicit action for returning to an earlier state in its navigation trajectory. It studies this recovery mechanism on two live web-navigation benchmarks under both zero-shot and fine-tuned settings.
ViMo predicts the next mobile-app screenshot after a candidate action by separately modeling graphics and text. A symbolic placeholder representation preserves layout while a second predictor supplies readable text, enabling visual lookahead for GUI-agent planning.
Studies whether mid-training on GUI perception, multimodal reasoning, and text reasoning transfers to GUI-agent planning. Experiments compare 11 task sources and curated mixtures using WebArena and AndroidWorld to investigate training-data choices when GUI trajectories are scarce.
Explorer collects interactable GUI elements from a live target application and records user sessions for application-specific model training. It links repeated interface states into a navigation map that supports path planning and voice-directed interaction.
SkillWeaver explores websites, practices interactions, and converts the resulting experience into a reusable library of callable skill APIs. Its WebArena and live-website experiments examine skill refinement, composition, and transfer from stronger agents to weaker ones.
Combines generalist and specialist models with hierarchical planning and multiple grounding methods for computer-use tasks.
Navi-plus evaluates GUI agents that ask follow-up questions to complete ambiguous user instructions. It provides GUI clarification question-answer pairs and Dual-Stream Trajectory Evaluation for this interactive setting.
Introduces GUI-Xplore exploration videos and downstream tasks, with an agent that combines action-aware modeling and graph-based environment reasoning.
This study compares matched reasoning and non-reasoning vision-language models on static mobile GUI tasks and interactive AndroidWorld navigation. It finds that chain-of-thought effects vary across tasks and model families.
Introduces V-Droid, which verifies candidate actions in a discrete action space rather than directly generating each mobile operation.
Separates planning from execution and creates synthetic plan annotations for training agents on extended web-navigation tasks.
Coordinates specialized Windows UI agents with dynamic task scheduling, shared memory, and human-triggered rollback for recovering from errors.
Combines rapid target prediction with deliberate interface analysis, adaptively selecting the grounding process according to task complexity.
Uses human-planned subtasks to constrain and refine the intermediate plans connecting user goals with executable mobile operations.
Introduces a modular visual web-agent stack with planning and memory components, exposed through a remote-browser application and Chrome extension.
Refines reusable high-level meta plans with execution feedback to guide language-agent planning across interactive environments.
Selects critical steps from expert interaction trajectories for targeted agent fine-tuning, studying efficiency and generalization across tasks.
Uses inference of possible user queries from screenshots and target coordinates as a training bridge between GUI grounding and action reasoning.
Uses active perception and hierarchical agents for instruction decomposition, progress tracking, action selection, and reflection in PC workflows.
Introduces desktop and web tasks with varied initial states to test planning recovery and adaptability beyond canonical starting configurations.
Uses variational subgoal-conditioned reinforcement learning to improve learning efficiency on sparse-reward mobile and web-control tasks.
Splits mobile tasks into reaching the required page and operating on it, using subtask data and preferred GUI trajectories for training.
Studies a screenshot-driven native GUI model with unified actions, deliberate reasoning, and iterative training on interaction traces.
Builds self-critique training examples from searched recovery paths to improve agents' ability to detect and correct errors during interaction.
Uses staged supervised training to combine GUI understanding and grounding with hierarchical reasoning and expectation-based reflection.
Combines PC Tracker interaction capture, completion of action and reasoning annotations, and planning and grounding agents for desktop workflows.
Uses screenshots, a unified action space, and staged grounding and reasoning training for cross-platform GUI interaction.
Separates interpretation of user instructions from precise GUI localization using general-purpose and specialized visual-language components.
Surveys virtual agents for browsers, applications and operating systems, organizing prior work by task type, observation and action spaces, model strategies and evaluation methods. It examines screen-based interaction and keyboard, mouse and touch control, alongside transferability and long-sequence decision-making challenges.
Presents a preliminary study of Claude 3.5 Computer Use across desktop tasks and software, analyzing planning, action, and critique behavior and providing a framework for deploying GUI-automation models.
Introduces WebDreamer, which simulates candidate web actions with language-model world models and value estimates before acting.
Introduces an orchestrated team of browsing, file, and coding agents with progress tracking and error recovery for general digital tasks.
Discovers compact intents from demonstrations and uses intent predictions to guide a language-model web agent's decisions and exploration.
OSCAR translates user instructions into Python control code while observing screen images and acting through mouse and keyboard operations. A state-machine controller handles errors and replans tasks during execution across desktop and mobile applications.
Studies how simplifying and aligning a web agent's observations and actions with language-model capabilities affects task completion.
Combines adaptive mobile-task planning, reflection-based recovery, and multiple memory components, evaluated with MobBench and AndroidArena.
Uses a learned web world model to predict important state changes and compare candidate actions before executing them.
Combines hierarchical planning, retrieved experience, and a computer interaction interface to execute multistep GUI tasks.
第 121–180 条，共 283 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。
