OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
Vimo: A generative visual gui world model for app agents
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 9polarities
background 3representative citing papers
HiViG is a test-time critic that combines macro-action history summarization with visual grounding of execution coordinates to reduce short-sighted and visually erroneous actions in long-horizon GUI agents.
BBCritic reframes GUI critique as continuous semantic alignment via contrastive learning in an affordance space, outperforming larger binary SOTA models on a new four-level hierarchical benchmark without extra annotations.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
MIRAGE compresses explicit chain-of-thought into latent vectors and adds a generative world model to predict future interface states, matching explicit reasoning performance with 3-5x fewer tokens on Android benchmarks.
UI-Oceanus shows that continual pre-training on forward dynamics predictions from synthetic GUI exploration improves agent success rates by 7% offline and 16.8% online, with gains scaling by data volume.
World models trained on delta text, full text, diffusion images, and renderable code achieve SoTA on two benchmarks and improve downstream GUI agent performance on three mobile datasets with modality-specific strengths.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.
citing papers explorer
-
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
-
A History-Aware Visually Grounded Critic for Computer Use Agents
HiViG is a test-time critic that combines macro-action history summarization with visual grounding of execution coordinates to reduce short-sighted and visually erroneous actions in long-horizon GUI agents.
-
Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment
BBCritic reframes GUI critique as continuous semantic alignment via contrastive learning in an affordance space, outperforming larger binary SOTA models on a new four-level hierarchical benchmark without extra annotations.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
MIRAGE compresses explicit chain-of-thought into latent vectors and adds a generative world model to predict future interface states, matching explicit reasoning performance with 3-5x fewer tokens on Android benchmarks.
-
UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics
UI-Oceanus shows that continual pre-training on forward dynamics predictions from synthetic GUI exploration improves agent success rates by 7% offline and 16.8% online, with gains scaling by data volume.
-
How Mobile World Model Guides GUI Agents?
World models trained on delta text, full text, diffusion images, and renderable code achieve SoTA on two benchmarks and improve downstream GUI agent performance on three mobile datasets with modality-specific strengths.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
-
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
A survey proposing a three-level capability taxonomy (L1 Predictor, L2 Simulator, L3 Evolver) for world models across physical, digital, social, and scientific domains.