SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety

arXiv:2609.36201 · cs.CL, cs.AI, cs.SE · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI, cs.SE

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/jc-244/SCOUT

Terminology

• Verifier — 83× in this paper · explained in 2 episodes
• Verification — 31× in this paper · explained in 2 episodes
• Trace — 18× in this paper · explained in 2 episodes
• Benchmark — 16× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 14× in this paper · explained in 3 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Benchmarking — 5× in this paper · explained in 3 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Agentic Coding — 1× in this paper · explained in 1 episode
• Agentic Search — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Generalizability — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
• ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
• Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
• The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
• SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
• Tree Search for Language Model Agents
• CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• The Art of Building Verifiers for Computer Use Agents
• Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification
• Kimi K2.5: Visual Agentic Intelligence
• GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
• Task-Adaptive Rubrics for GUI Reward Modeling
• A-MEM: Agentic Memory for LLM Agents
• ZeroGUI: Automating Online GUI Learning at Zero Human Cost
• ReAct: Synergizing Reasoning and Acting in Language Models
• ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering