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

SafeMCP is a server-side defense plugin that uses look-ahead reasoning to proactively filter and constrain tool acquisition for LLM agents, thereby mitigating catastrophic risks associated with expand…

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…

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…

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

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…

The paper introduces Governed MCP, a kernel-resident gateway that enforces comprehensive, robust tool governance for AI agents' privileged tool calls, significantly improving safety beyond userspace m…

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…

The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.

The paper introduces OpenClawBench, a large-scale dataset and framework for measuring process-side anomalies in real-world agent execution trajectories, demonstrating that task success does not guaran…

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 ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated in…

The paper introduces T-MAP, a trajectory-aware evolutionary search method, to discover and generate multi-step adversarial prompts that exploit vulnerabilities in autonomous LLM agents through tool ex…

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

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

LiSA introduces a conservative policy induction framework that enhances fixed AI guardrails by converting sparse, noisy failure reports into reusable, generalized policies, significantly improving saf…