CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering

arXiv:2609.32600 · cs.AI, cs.SE · Submitted 2026-09-26 · Read on arXiv

cs.AI, cs.SE

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/THUDM/slime

Terminology

• Verifier — 49× in this paper · explained in 2 episodes
• Verification — 35× in this paper · explained in 2 episodes
• Benchmark — 34× in this paper · explained in 2 episodes
• Trace — 12× in this paper · explained in 2 episodes
• Aggregation — 8× in this paper · explained in 1 episode
• Consistency — 7× in this paper · explained in 3 episodes
• Core — 7× in this paper · explained in 2 episodes
• Calibration — 6× in this paper · explained in 7 episodes
• Provenance — 6× in this paper · explained in 4 episodes
• Benchmarking — 5× in this paper · explained in 4 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• GRPO — 3× in this paper · explained in 6 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Action Space — 2× in this paper · explained in 1 episode
• Credit assignment — 2× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reward Shaping — 1× in this paper · explained in 2 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• Programming with Pixels: Can Computer-Use Agents do Software Engineering?
• Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
• Evaluating Large Language Models Trained on Code
• GameDevBench: Evaluating Agentic Capabilities Through Game Development
• Mind2Web: Towards a Generalist Agent for the Web
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
• WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
• On the Effects of Data Scale on UI Control Agents
• WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
• GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
• SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• OpenCUA: Open Foundations for Computer-Use Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection