已审阅并标注「强化学习」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。
GUI-SAGE generates reasoning conditioned on known actions and weights policy updates using confidence and reward signals. Its experiments use AndroidControl and GUIOdyssey data and separately evaluate interactive AndroidWorld tasks.
Introduces PhoneWorld, which converts observed app pages, transitions and state changes into executable Android environments through a build-inspect-repair process. Generated tasks and programmatic verifiers support benchmarking, trajectory collection and online training.
Describes asynchronous reinforcement-learning infrastructure using parallel cloud-hosted Android instances, explicit task lifecycles, and persistent-state management for mobile GUI interaction.
Introduces MobileGym, a browser-hosted simulation of mobile app interactions whose configurable JSON state supports deterministic judging and parallel rollouts. MobileGym-Bench adds parameterized tasks, with experiments examining online training and transfer to real devices.
Presents CUA-Gym, which co-generates instructions, initial and target states, and executable reward checks through generator-discriminator iterations. Mock web applications expand training environments, with learned agents evaluated on OSWorld-Verified and WebArena.
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.
DUDE combines asymmetric hybrid-reward learning with summaries of deceptive-interface failures to guide safer web actions. Its RUC benchmark evaluates deception susceptibility alongside ordinary task performance across interface scenarios.
Introduces Weblica, which combines HTTP-level capture and replay with website-grounded environment synthesis. The resulting interactive web environments support reinforcement learning and tests of navigation transfer and inference-time scaling.
Introduces Faithful-Agent, which first teaches abstention under perturbed evidence and then refines GUI policies with an anchor-based, variance-adaptive advantage estimator. A thought-action consistency reward encourages decisions grounded in displayed evidence and instructions.
Trains a GUI grounding proposer together with a visual critic that evaluates candidate locations rendered on screenshots. An adaptive reinforcement-learning schedule balances their development, using proposal diversity and critic feedback during training.
WebAgentGuard separates prompt-injection detection from the operating web agent through a parallel multimodal guard. The guard is trained on synthetic visual/textual examples using reasoning-focused supervised fine-tuning followed by reinforcement learning.
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.
Introduces Android Coach, which uses a learned critic to evaluate multiple candidate actions at each observed emulator state. Process rewards and a group-wise advantage estimator support online training, evaluated on AndroidLab and AndroidWorld.
Introduces VeriGUI, which checks expected action effects and reasons about recovery before subsequent GUI actions. Training combines synthetic failure trajectories with verification-weighted GRPO, evaluated on an AndroidControl-based robustness benchmark.
The framework separates inference-time subgoal planning from MiRA, a reinforcement-learning method that supplies milestone rewards. WebArena-Lite experiments evaluate these mechanisms for long-horizon web navigation.
Presents OS-Themis, a multi-agent critic that divides GUI trajectories into verifiable milestones and reviews their evidence before assigning an outcome. OGRBench evaluates GUI rewards across platforms, with AndroidWorld experiments examining training and trajectory filtering.
Combines instruction rewriting with conditional second-stage zooming for small GUI targets. A grounding dataset and GRPO training support joint prediction of click coordinates and element bounding boxes.
Introduces VeriEnv, which recreates websites as executable training environments and exposes internal state through a Python SDK for task generation and deterministic reward checks. Experiments examine web-agent learning across new and expanded site environments.
Presents a Chinese mobile GUI dataset and navigation benchmark together with SecAgent, which compresses previous screenshots and actions into semantic summaries. The agent is trained with supervised and reinforcement fine-tuning to use this compact interaction context.
Introduces AndroidWorld-Generalization with separate tests for unseen task instances, templates, and applications. A GRPO training system combines containerized environments with asynchronous trajectory collection to study these generalization regimes.
Introduces WebFactory, a GUI-agent training pipeline that synthesizes websites, generates tasks and trajectories, and trains with decomposed rewards. Offline and online transfer evaluations examine agents trained on the generated environments.
Studies webpage injections that affect both screenshots and accessibility trees, then trains web agents through teacher imitation, supervised adversarial examples, and adversarial reinforcement learning. The evaluation tests defenses on MiniWoB++ and held-out tasks.
Combines supervised and reinforcement fine-tuning for continual GUI learning, using policy entropy to adjust their proportions and gradient projection to limit conflicting updates. AndroidControl-CL groups applications into sequential tasks to evaluate adaptation and retention.
Presents GUI-Owl-1.5 variants and a hybrid data pipeline for multimodal GUI interaction, tool use, memory, and multi-platform tasks.
GUI-GENESIS reconstructs applications as lightweight web environments with executable assertions for reward computation. It evaluates the cost of these training environments and transfer from synthetic interaction training to held-out real tasks.
This framework learns an agentic-Q model to estimate individual actions’ contributions to GUI task completion. It then optimizes a policy with step-level samples from its own trajectories, decoupling policy updates from environment interaction.
OpAgent combines multi-task GUI fine-tuning with online web reinforcement learning using outcome judgments and rule-based progress rewards. A modular planner, grounder, reflector and summarizer support navigation and recovery, evaluated separately from the underlying trained policy.
ADMIRE extracts milestones from successful GUI explorations to provide adaptive intermediate rewards. It assigns credit differently to successful and failed trajectories and evaluates training on AndroidWorld, with additional transfer studies in web and embodied settings.
ACuRL uses autonomous interface exploration and an adaptive task curriculum to continually train computer-use policies with reinforcement learning. CUAJudge supplies outcome feedback, and experiments study adaptation across desktop applications and environment changes.
Code2World predicts future GUI screens through renderable code, trained on AndroidCode trajectories with supervised learning and render-aware reinforcement learning. It evaluates visual prediction and downstream AndroidWorld navigation with the learned world model.
Describes a GUI-agent family combining broad intermediate training, full-trajectory online reinforcement learning, and merging of specialized models.
Studies GUI-grounding development from a weakly grounded base model through data preparation, visual training, and verifiable rewards.
UI-Mem stores workflows, skills and failure patterns as reusable templates to guide online GUI reinforcement learning. It varies guidance within rollout groups and continually updates the memory so an unguided policy can learn from guided experiences.
DynaWeb learns a world model that predicts web-page representations after actions and uses it to generate policy-training rollouts. It interleaves these rollouts with expert trajectories and evaluates the trained web agents on WebArena and WebVoyager.
WebArbiter generates reasoned action-preference verdicts for web navigation, using reasoning distillation followed by reinforcement learning. It introduces WebPRMBench and evaluates both preference judgments and reward-guided trajectory search.
Continual GUI Agents defines grounding under changing application domains and screen resolutions. Its GUI-AiF training framework uses separate point- and region-alignment rewards to adapt grounding as these distributions shift.
OmegaUse combines exploratory and taxonomy-guided data synthesis with supervised fine-tuning followed by GRPO for GUI control. The report introduces OS-Nav for offline Android and Ubuntu evaluation alongside established grounding and action-prediction benchmarks.
CCPO couples GUI policy optimization with coordinate-guided compression of past visual observations. It aggregates targets across rollouts to focus retained context and uses distance-based advantages to train grounding and compression together.
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.
BEPA adapts a small set of expert GUI traces into policy-aligned guidance through trajectories reachable by the learner and a dynamically updated task cache. It evaluates this two-level approach to reinforcement learning on desktop and web benchmarks.
InfiniteWeb generates functional, interconnected websites and task evaluators using shared specifications and task-driven development. It evaluates website construction and the transfer of GUI policies trained in these synthetic web environments to OSWorld and Online-Mind2Web.
WebGym supplies realistic web tasks with rubric-based evaluation and an asynchronous rollout system for reinforcement learning. It studies how training on an agent’s own interaction traces scales with task coverage and transfers to unseen websites.
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.
OS-Oracle synthesizes GUI critic examples and trains a pre-action critic with supervised learning followed by consistency-preserving GRPO. It introduces OS-Critic Bench across mobile, web, and desktop settings and tests critic-assisted agents in OSWorld and AndroidWorld.
Introduces GUI Exploration Lab, a simulation engine for composing screens, interface elements, and navigation graphs. It studies how supervised learning, single-turn RL, and multiturn RL affect GUI navigation and exploration.
This work trains high-level schedulers with staged reinforcement learning driven by execution feedback. Its CES framework separates a Coordinator for planning and decomposition, a StateTracker for compressed context, and a low-level Executor.
Co-EPG alternates reinforcement learning for a planner with updates to a grounding model using generated training examples. The evolving grounder provides feedback to the planner, and evaluation uses Multimodal Mind2Web and AndroidControl.
HAR-GUI combines episodic reasoning and short-term memory to use earlier interactions when selecting GUI actions. Its training constructs reflective scenarios and correction guidance and applies a hybrid reinforcement-learning reward to the 3B policy.
OSGym supplies full operating-system sandboxes with GUIs for parallel computer-use data collection and training. It combines per-replica state management, hardware-aware orchestration, copy-on-write virtual-machine disks, and layered failure recovery.
GroundCUA turns expert desktop demonstrations into densely annotated screenshots and grounding instructions. The GroundNext model family uses this supervision and subsequent reinforcement learning, with both grounding benchmarks and an OSWorld agent configuration used for evaluation.
HyperClick trains GUI grounders to produce a click and an accompanying confidence estimate using rewards for correctness and confidence alignment. Its evaluation examines localization, calibration, and abstention behavior.
Combines structured progress-and-decision reasoning with history summarization to improve cross-domain generalization in GUI navigation agents.
OpenPhone trains a compact mobile policy with supervised learning followed by GRPO on synthetic GUI data, incorporating reasoning and memory management. Its device-cloud design handles routine work locally and delegates complex subtasks, with online evaluation on AndroidLab.
Treats alternative instruction formulations as reasoning paths and trains GUI-grounding models to select and combine useful perspectives.
UltraCUA trains a shared policy for primitive GUI actions and high-level tool calls using synthesized tasks and hybrid trajectories. Supervised fine-tuning followed by online reinforcement learning is evaluated on OSWorld and WindowsAgentArena.
WebServ combines copy-on-write container environments with a compact DOM-derived browser interface for training web agents. Network-aware waiting supports action execution in single-page applications, with evaluations and reinforcement-learning experiments on WebArena-Lite.
Introduces Hi-Agent, jointly training a high-level reasoning model and a low-level mobile action model. Execution feedback supplies a foresight advantage for optimizing subgoal decisions, with evaluations on Android control benchmarks.
WARC-Bench packages dynamic web pages as replayable archives and evaluates short navigation subtasks involving components such as date pickers and scrollable containers. It also studies supervised training followed by reinforcement learning with verifiable rewards on these browser interactions.
Ferret-UI Lite develops a 3B GUI agent using mixed real and synthetic data, reasoning with visual tools at inference, and reinforcement learning. It evaluates grounding and navigation across mobile, web, and desktop settings, including AndroidWorld and OSWorld.
AutoPlay explores application states and functions to generate tasks, then uses a model executor and verifier to construct demonstrations. It produces 20,000 tasks across 20 Android apps and 10,000 tasks across 13 Ubuntu apps for supervised and reinforcement learning of UI agents.
第 61–120 条，共 242 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。
