AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- Constitutional AI: Harmlessness from AI Feedback
- JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
- InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
- OR-Bench: An Over-Refusal Benchmark for Large Language Models
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
- WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents
- Let's Verify Step by Step
- AgentBench: Evaluating LLMs as Agents
- ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
- Training language models to follow instructions with human feedback
- Ignore Previous Prompt: Attack Techniques For Language Models
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