Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.Advances in Neural Information Processing Systems, 37:52040–52094
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
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.
citing papers explorer
-
Covering Human Action Space for Computer Use: Data Synthesis and Benchmark
Presents CUActSpot benchmark and renderer-LLM data synthesis that lets a 4B model outperform larger open-source models on complex computer interactions.
-
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
-
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
-
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.
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning