The paper introduces SafeMed-R1, a clinically audited LLM that significantly improves safety and ethical alignment for medical applications, matching or exceeding resident performance on safety-critic…

The paper introduces DrugClaw, a multi-agent system, and DrugAudit, a new benchmark, demonstrating that DrugClaw excels at answering drug-related questions by grounding answers in primary regulatory s…

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 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.

The paper proposes a medication-aware framework that integrates medication adherence with financial transaction monitoring to significantly improve the detection of financial exploitation in Alzheimer…

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 introduces SafeAudit, a meta-audit framework that systematically enumerates test cases and uses a quantitative metric to uncover significant residual unsafe behaviors in LLM agents that exis…

UniD$^3$ is a novel Knowledge Graph-enhanced RAG framework that processes vast biomedical literature to systematically extract, organize, and validate comprehensive drug-disease knowledge, achieving h…

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…

CAREAgent is a novel agent designed for fine-grained clinical order generation, achieving significant performance improvements on unseen benchmarks by integrating structured reasoning and tool usage.

The paper introduces SURGENT, a multi-agent assistance system designed for the entire perioperative workflow, which outperforms standard LLMs by providing context-aware, traceable, and privacy-preserv…

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 EHRBench, a large-scale, automated, and reliable benchmark derived from real Electronic Health Records (EHRs) to rigorously evaluate the clinical decision-making capabilities of L…

This study benchmarks four local LLMs for natural-language-to-SQL querying in biopharma manufacturing, finding that general-purpose code-tuned models like Llama 3.1 8B and Qwen 2.5 Coder 7B outperform…

This paper introduces AgentREVEAL, a diagnostic framework showing that the utility of web retrieval in LLM agents creates a safety-utility trade-off, as relevance itself can degrade safety alignment a…

This paper introduces AgentREVEAL, a diagnostic framework that demonstrates that the utility of web retrieval in LLM agents creates a safety-utility trade-off, as relevance itself can degrade safety a…

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 ARSM-Agent, a full-link security enhancement framework, to significantly improve the adversarial robustness and security of large language model agents used for critical medical dec…