已审阅并标注「世界模型」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。
Separates next-screen prediction from action evaluation in GUI lookahead and trains Direct Action Ranking on reference actions, comparing prediction-augmented scoring under matched offline supervision.
Replaces future-screenshot generation with a shared latent representation for GUI action selection and action-conditioned transition prediction. An action-aware contrastive objective encourages the transition representation to retain discriminative action-induced changes.
Presents LGWM, a decoder-free GUI world model that predicts the next screen representation from an action and compares it with the observed state to verify transitions. Its paired diagnostic separates legitimate and hijacked transitions that lead to the same credential screen.
Presents AdvSim2Real, which jointly adapts web-task curricula, prompt-injection adversaries, and agent policies inside a frozen web world model. It evaluates robustness against an unseen adversary and transfer from simulated interaction to a real browser.
Introduces Infinite-Dreamer, which learns action-conditioned screenshot editing from structured descriptions of GUI changes and uses it to synthesize robustness examples and multi-step trajectories. The synthetic data trains a mobile GUI agent evaluated on AndroidWorld, MobileWorld, and AndroidControl-Curated.
Compares fine-tuned, retrieval-based and hybrid language-model world models for next-observation prediction and action selection in text environments including WebShop.
Introduces AutoGUIWorld, which combines task planning and image editing to synthesize action-grounded GUI trajectories without running the depicted software. It filters generated transitions and tests whether training on them improves agents operating real desktop and scientific applications.
Presents PrecogUI, which retrieves prior anomaly and success patterns and predicts symbolic UI transitions before choosing actions. It also introduces InterfereBench, generated for evaluating long GUI workflows with disruptive events and recovery requirements.
Introduces StateAliasBench to isolate GUI world-model ambiguities in which matching visible screens and actions can lead to different futures. It augments frozen world models with structured state recovered from interaction history and evaluates the effect on prediction and agent execution.
Trains discriminative web world models to distinguish the true next state from outcomes of alternative actions. Branching web trajectories support training, followed by tests of predicted-state matching, process-reward action ranking and end-to-end WebArena-Lite selection.
Introduces GUI-CC, a benchmark for assessing GUI world models as multi-step agent environments. Separate reference-action and agent-loop tracks test whether generated screens preserve context, plausible transitions, and task progress throughout interaction.
Uses learned world models for mobile-agent training rollouts and for reasoning about the consequences of candidate GUI actions.
AppDeltaWorld predicts executable code updates for the next mobile UI state, using transition-constrained retrieval and rendered visual assets. It evaluates reconstruction fidelity separately from policy training and adaptation using generated environments.
Introduces State Transition Pretraining, which jointly learns to infer actions from GUI changes and predict future states from current screens and actions. Subsequent instruction-trajectory fine-tuning tests whether these representations transfer to desktop and mobile agent tasks.
Introduces EvoGUI, which derives temporal ordering, inverse action/value prediction, and successor-discrimination probes from recorded GUI trajectories. Its web-derived benchmark isolates transition understanding from the other abilities involved in end-to-end task success.
Uses instruction screening and a safety-augmented world model to assess likely consequences of mobile GUI actions before execution.
Compares mobile world models that predict state changes as delta text, full text, images or renderable code. Downstream Android benchmarks examine synthetic training trajectories and test-time guidance, including limits of post-action reflection.
Presents a desktop world model that predicts textual UI changes before synthesizing the next screenshot. It learns from Microsoft Office transitions and is evaluated by letting a frozen agent compare simulated actions before execution.
Introduces WebWorld, an open-web simulator trained on interaction trajectories for generating agent training data and testing candidate actions. WebWorld-Bench evaluates simulated transitions, alongside downstream web-agent training experiments.
UI-Oceanus converts autonomous GUI exploration and execution feedback into supervision for predicting future interface states. It compares forward and inverse objectives during continual pretraining and examines downstream offline and online navigation as synthetic data scales.
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.
GUI-GenBench tests image-generation models as action-conditioned GUI environments across five suites, including transitions, trajectories and grounding. Its VLM-based GUI-Score separates goal completion, interaction logic, consistency and visual properties.
SafePred uses world-model risk forecasts to guide action filtering and task replanning. Its desktop and web safety evaluations distinguish policy compliance, task success and success under the specified policy.
gWorld predicts future mobile GUI states as renderable web code and supplies an automated pipeline for code-based training data. The study evaluates visual state prediction and how stronger world models affect downstream mobile policies.
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.
MobileDreamer predicts post-action GUI states as task-relevant textual sketches with an order-invariant learning objective. Agents use these predictions for lookahead action selection, evaluated on AndroidWorld.
Evaluates semantic world models for mobile interfaces and studies natural-language state transitions as a tool for agent planning.
R-WoM evaluates how well world models predict nearby GUI states, align complete procedures, and recognize milestone transitions. It retrieves external tutorials to guide simulated future interactions, with experiments on subsets of OSWorld and WebArena.
SEAgent explores unfamiliar software using a world-state assessor and an automatically generated task curriculum. It learns from failed and successful interactions through adversarial imitation and GRPO, then combines specialist experience into a generalist agent evaluated on five OSWorld software environments.
Trains ScreenExplorer with reinforcement learning in dynamic GUI environments, using a world-model curiosity reward and experience-stream distillation to support sustained exploration.
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.
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.
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.
Trains GUI agents with a frozen value model learned from offline interactions, guiding action exploration without predicting complete next observations.
Introduces WebDreamer, which simulates candidate web actions with language-model world models and value estimates before acting.
Uses a learned web world model to predict important state changes and compare candidate actions before executing them.
Textual Foresight learns UI representations by describing the future screen expected after an action on the current interface. The OpenApp dataset supports pretraining and downstream evaluation of representations that connect individual elements with whole-screen changes.
HTML and annotation release used for Code2World’s action-conditioned GUI-state prediction training, constructed from mobile GUI trajectories.
Web-world-model training data with prompts, images, action descriptions, and responses, released with the WebDreamer project.
Two JSONL collections for supervised fine-tuning the WebEvolver agent policy and web world model.
Released GUI world-model checkpoint that turns a screenshot and proposed action into HTML for rendering a predicted next screen.
WebDreamer model checkpoint that predicts the consequences of web actions from screenshots and textual descriptions.
World-model and planning components that simulate web-action outcomes, with linked training data and model checkpoints.
Component for web-agent trajectory collection, supervised-data preparation and world-model-based trajectory synthesis.
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。
