Measuring Harmfulness of Computer-Using Agents

arXiv:2508.00935 · cs.CR, cs.AI · Submitted 2025-07-31 · Read on arXiv

cs.CR, cs.AI

Submitted: 2025-07-31

Updated: 2026-09-03

Terminology

• Benchmark — 33× in this paper · explained in 2 episodes
• Agentic Framework — 11× in this paper · explained in 6 episodes
• Alignment — 10× in this paper · explained in 1 episode
• Computer-Using Agent — 9× in this paper
• Benchmarking — 5× in this paper · explained in 3 episodes
• Robustness — 5× in this paper · explained in 5 episodes
• Verifiable Rewards — 5× in this paper · explained in 2 episodes
• Scaffolding — 4× in this paper · explained in 3 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• Core — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Agentic System — 1× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) Reasoning — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes

Sources

• Agent S: An Open Agentic Framework that Uses Computers Like a Human
• Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
• AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
• Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
• JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
• Evaluating Large Language Models: A Comprehensive Survey
• The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
• SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
• ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
• ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models
• Identifying the Risks of LM Agents with an LM-Emulated Sandbox
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming
• SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
• R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
• InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models
• Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
• SafetyBench: Evaluating the Safety of Large Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs