The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unad…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…

The paper introduces SABER, a new benchmark that evaluates the operational safety of LLM coding agents in complex, stateful project environments, finding that current models have a high rate of harmfu…

The paper introduces TraceSafe-Bench, a comprehensive benchmark, and finds that securing LLM agents requires jointly optimizing for structural reasoning and safety alignment to mitigate risks during m…

EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

The paper proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance…

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

AgentTrust is a novel runtime safety layer that intercepts and evaluates AI agent tool calls before execution, achieving high accuracy in detecting unsafe actions across complex and obfuscated scenari…

AgentWall is a runtime safety layer that intercepts and evaluates all proposed actions from local AI agents against a declarative policy, ensuring safety before execution.

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper proposes and evaluates symbolic guardrails as a practical method to provide strong, verifiable safety and security guarantees for domain-specific AI agents without compromising their utility…

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks…

The paper introduces Owner-Harm, a formal threat model addressing the critical blind spot of AI agents harming their own deployers, demonstrating that specialized defenses are needed beyond generic sa…

The study evaluates how safety alignment affects autonomous security agents using a comprehensive trace-based benchmark, finding that while less-restricted models show gains, these effects are not uni…