已审阅并标注「工具集成」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。
WildAWM synthesizes resettable GUI/MCP/CLI environments and cross-interface tasks, using execution-based checks of solvability, difficulty and verifier consistency before supervised and reinforcement learning.
CUA-Lite unifies environment interfaces, supervised data formats and per-model harnesses for evaluation, reinforcement learning and supervised fine-tuning across desktop, browser and mobile tasks.
Trains native computer-use models to coordinate GUI actions and code execution using hybrid demonstrations and online reinforcement learning.
Introduces an open generalist computer-use stack combining visual and programmatic interaction, with model-controlled observation and task-state decisions.
Benchmarks agents creating editable Blender projects through shell, Python and MCP tools, judging delivered scenes with multi-view renders, task-specific rubrics and visual-quality ratings.
Measures source-attribution limits in Android accessibility and separately tests application-history and selected-WebView-object checks for authorizing AppFunctions actions.
Introduces OpenMobile-2, combining simulated mobile apps, emulator tasks, released training data, and policies that can alternate GUI interaction with app-native tools.
Introduces Web$hell, an interface that compiles live pages into persistent information and action objects so agents can gather evidence, navigate websites, and reuse acquired content through shared operations.
Studies a minimal terminal-based execution framework that lets digital agents construct tools and manage context across browser, desktop, and CAD tasks.
Trains computer agents on verified GUI, command-line, and interleaved trajectories to learn when and how to combine interaction modes.
Introduces SCOUT, a safety verifier that first derives task-specific completion and safety rubrics from a computer-use trajectory, then actively probes the resulting environment for evidence. It evaluates whether these two stages detect harmful consequences that screenshots alone can miss.
Introduces CUA-SWE, a benchmark and execution environment that combines code changes with graphical interaction and visual inspection of running software. Task-specific tests verify repairs and changes whose required information may be available only through the application interface.
GUI-Hopper combines verified Android deeplinks with GUI actions, using landing-screen descriptions, hybrid trajectory training and reinforcement learning to select navigation shortcuts and recover through GUI control.
MintAct trains a visual-agent family for grounding, navigation and tool use across mobile, desktop and web environments. Its shared infrastructure supports trajectory collection and asynchronous online RL while controlling cross-domain sampling and off-policy drift.
RecreationWorld gives hybrid agents running reference applications to explore and recreate using native GUI controls and coding tools. Its multi-platform benchmark checks interaction-dependent behavior with programmatic and visual assertions, while trajectory-training transfer is evaluated separately.
AutoTailor compiles web trajectories into reusable browser-automation APIs, then filters and dynamically revises the capability inventory. WebArena experiments distinguish API-only operation from an agent that can fall back to ordinary reasoning and browser actions.
DroidTool generates application-state tools through proposal, implementation, testing and repair. Relational tests connect the tools’ preconditions and effects, and the resulting tools are evaluated as additions to Android GUI agents.
Turns desktop applications into reproducible GUI-and-CLI environments and generates verified hybrid trajectories for agent post-training.
ASIL exposes application state as structured JSON and provides code-executable semantic actions. Its application benchmark compares this interface with screenshot control and application-native APIs, and studies supervised and reinforcement learning on the structured interface.
Proposes WebMCP-Phalanx, a browser-integrated runtime that binds page-exposed tools to their registering principals and separates content inspection from privileged invocation. It studies lifecycle and prompt-injection attacks, including a timing bypass that motivates validating all visible metadata before tool use.
This study separates tool-adoption behavior from task competence in hybrid GUI–MCP agents. It tests tool-use incentives and screenshot-history compression, showing why changed action preferences alone need not improve held-out accuracy.
Describes a foundation GUI agent with combined GUI and command-line actions, large-scale interaction infrastructure, and iterative environment and task generation.
Introduces an Interactive Reward Agent that proposes completion conditions and verifies them using system, application, and GUI tools after execution. GUI-RewardBench provides annotated desktop trajectories for evaluating these evidence-based judgments and their use in reinforcement learning.
Introduces StateAct, a code-first computer-use harness that manipulates program state directly and delegates screenshot-and-click subgoals to a GUI agent. An independent completion gate checks saved outputs, while fresh subagents handle subgoals to limit accumulated context.
OpenForgeRL connects stateful agent harnesses to reinforcement-learning infrastructure through a model-call recording proxy and isolated rollout containers. Its validation includes browser and computer-use agents, alongside tool-oriented agents, and examines how harness choice affects learned reliability.
Tactile turns accessibility, OCR and visual evidence into explicit desktop targets with executable actions and verification cues. Its execution loop chooses semantic actions or coordinate fallbacks while retaining provenance for replay and diagnosis.
LUMOS converts native accessibility metadata and browser UI structure into semantic interface blueprints with stable element identifiers and available actions. It combines live pointer-to-element grounding with an observe-act loop constrained to visible-UI primitives.
This benchmark matches desktop goals, initial states and final-state verifiers across screen-only GUI and skill-mediated CLI agents. Its experiments separate graphical execution failures from missing CLI skill coverage, including a verifier-guided skill-augmentation condition.
Introduces macOS tasks spanning GUI and command-line interaction, with deterministic checks and intermediate-progress scoring for application workflows.
This study compares general coding agents using mobile command-line access with reproducible GUI agents on AndroidWorld and MobileWorld. It also supplies oracle CLI analyses and a separate task suite for operations such as bulk changes, filtering and hidden device state.
VISUALSKILL organizes application-specific text and figures into hierarchical skills retrieved on demand through an MCP tool. Skills combine authored documentation with live UI exploration, and matched multimodal/text-only comparisons test their utility for interface identification and workflow-state verification.
PhoneHarness routes phone workflows across GUI actions, device-side commands and host tools while retaining auditable execution traces. Its accompanying benchmark checks observable task side effects, separating mixed-action execution from plausible final-answer generation.
ComAct proposes COM program synthesis as an alternative interface for manipulating professional software and introduces ComCADBench with GUI-based comparison agents. ComActor adds a staged training and correction approach, supported by a Windows-container training platform.
WeaveBench requires agents to combine GUI, command-line and code operations within long tasks on an Ubuntu desktop. A trajectory-aware judge checks deliverables and interaction evidence, including shortcut behavior that outcome-only grading can miss.
CLI-Anything argues for application interfaces built around structured commands, explicit state and execution feedback. It describes transforming existing software into command-line harnesses and organizing that approach through CLI-Hub.
Agent JIT compilation turns browser task descriptions into validated executable plans containing model calls, tools and parallel work. A cost-based scheduler and pre/postcondition protocol target latency and incorrect tool use in web-agent execution.
Argues for compiling web tasks into predefined execution graphs before exposing an agent to untrusted runtime content. Its WebArena task analysis identifies typed, semantically complete website tools as a prerequisite and distinguishes this interface proposal from reactive click-level control.
ToolCUA synthesizes interleaved GUI/tool trajectories and trains agents to choose between graphical actions and higher-level tools. Staged supervised and reinforcement learning culminate in online hybrid-environment training with a reward for efficient execution paths.
MultiMedia-TerminalBench evaluates agents that use terminal tools to work with audio and video files. The Terminus-MM harness adds multimedia perception to study how accessible evidence changes executable workflows and task outcomes.
This study compares specialized, computer-use and coding agents on scientific visualization workflows. It examines GUI, CLI, code and tool-call interaction modes, including how persistent memory changes performance across repeated trials.
VLAA-GUI combines mandatory checks for visually supported completion, multi-tier loop recovery and on-demand workflow search. Optional coding and grounding agents support execution, with component ablations on Linux and Windows GUI tasks.
AgentClick gives terminal-based agents a browser review interface for plans, drafts, execution traces and editable memory. A local server and skill plugin let users inspect proposed actions and provide structured feedback.
UI-Copilot separates GUI execution from on-demand memory retrieval and numerical assistance. Its training procedure treats tool selection and multi-turn task execution as distinct optimization targets while keeping persistent observations outside transient context.
Presents ClawGUI, a shared harness for GUI-agent reinforcement learning, benchmark evaluation and deployment on mobile devices. It combines parallel virtual and physical environments, process rewards, and hybrid CLI-GUI execution with persistent memory.
EE-MCP studies application-dependent mixtures of GUI actions and MCP calls using generated environments, trajectory collection and filtered training. An experience bank extracts rules from trajectory comparisons for inference-time improvement, distinct from model distillation.
This position paper derives interface design principles from terminal-based human-agent collaboration: representational compatibility, transparent actions and low participation barriers. It argues that graphical and other agent-facing modalities should provide these properties explicitly.
EmbeWebAgent embeds agent access into existing web applications through frontend observations and a page-specific function registry. Its workflow combines GUI primitives, composite actions and MCP tools, demonstrated in a live interface.
Presents GUI-Owl-1.5 variants and a hybrid data pipeline for multimodal GUI interaction, tool use, memory, and multi-platform tasks.
This survey organizes agent skills by architecture, acquisition, deployment and security, including their role in computer-use systems and GUI grounding. It also proposes a permission and lifecycle governance framework for skill deployment.
VAGEN verifies GUI trajectories by first extracting readily available evidence and escalating to tool-based environment probes when needed. Evaluation on OSWorld-Verified and AndroidWorld studies verification accuracy and its cost.
ToolTok represents GUI operations with learned tool tokens and frames interaction as progressive tool selection. Semantic anchoring and an easy-to-hard curriculum teach tool meanings before visual pathfinding, with evaluation across grounding scenarios.
CUA-Skill encodes Windows application knowledge in parameterized skills and execution/composition graphs. Its agent retrieves and instantiates these skills and uses memory for failure recovery, with end-to-end evaluation on WindowsAgentArena.
GUI-Eyes trains GUI grounders to decide when and how to use visual tools such as crops and zooms. Its coarse-to-fine policy uses dense spatial rewards based on location proximity and region overlap, with evaluation on ScreenSpot-Pro.
OS-Symphony coordinates milestone-based reflection and memory with tools that build visually aligned tutorials through browser interaction. The framework evaluates trajectory correction and adaptation on online computer-use benchmarks including OSWorld.
NestBrowse organizes browser actions in a nested framework that separates interaction control from page exploration. It evaluates this design for deep information seeking beyond snippet retrieval and direct URL fetching.
MAI-UI combines GUI navigation, native user interaction, and MCP tool calls in a family of policies trained through generated data and online reinforcement learning. The report also studies device-cloud routing and scaling of parallel environments and interaction budgets, with grounding and Android navigation evaluation.
Introduces long mobile workflows that combine agent-user interaction, cross-application tasks, and MCP-based tool access.
Step-GUI uses calibrated trajectory rewards to turn generated GUI interaction data into training signals for compact agent models. The report also introduces GUI-MCP for hierarchical GUI operations and local task delegation, and AndroidDaily for static-action and end-to-end mobile evaluation.
Reports architectural and security lessons from building a browser agent, including hybrid accessibility-tree and visual context, browser tooling and programmatic constraints. A WebGames evaluation accompanies the discussion of reliability and specialization.
OSWorld-MCP evaluates how agents choose between GUI operations and MCP tool calls in computer tasks. It combines generated and curated tools, with 158 manually validated tools across seven applications, to examine tool use alongside task completion.
第 1–60 条，共 136 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。
