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…

The paper proposes a Risk Horizon Profiling (RHP) module that uses a continuous potential field model to profile future risk distributions, significantly improving trajectory prediction accuracy in bo…

The paper introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

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 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 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…

FALAT is a diagnostic framework that treats failure attribution in complex LLM agent trajectories as a dependency-guided search problem, successfully identifying both the responsible agent and the dec…

GLiNER Guard (GLiGuard) introduces a unified, efficient encoder family that simultaneously performs safety classification and PII detection in a single forward pass, offering a practical, low-cost alt…

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 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.

RiskFlow is a novel framework that generates realistic and safety-critical multi-agent traffic scenarios by reformulating trajectory generation as a single-pass transport problem in the action space.

The paper proposes BitTP, a lightweight bitlinear architecture that quantizes LLM-based trajectory predictors to 1.58-bit weights while keeping activations full-precision, enabling high-performance de…

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 addresses the lack of user understanding regarding the actions and residual effects of advanced computer-use agents by proposing AgentTrace, a traceability framework for visualizing agent be…

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 paper introduces 'probe trajectories'—a continuous measure of a concept's probability across a model's reasoning process—to improve the monitoring of Large Reasoning Models' future behavior, showi…