The paper introduces alignment contracts, a formal framework for specifying and enforcing behavioral constraints over observable effect traces, ensuring that powerful agentic security systems operate…

This paper proposes a method for ensuring safety in multi-agent reinforce learning through decentralized execution, using a shared global specification and a non-stationary multi-armed bandit.

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 ML-Bench, a policy-grounded multilingual safety benchmark, and ML-Guard, a superior guardrail model that enables culturally and legally aligned safety assessment for LLMs across 1…

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…

The paper presents ACD$^3$-GAT, a safety-contract graph MARL framework for network security response systems, which adds budget context, CVaR estimation, opponent-belief state, and Graph Counterfactua…

The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM s…

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 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 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…

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

This paper comparatively evaluates DKnownAI Guard against three competitors, demonstrating that DKnownAI Guard achieves superior performance in detecting both agent-specific threats and harmful conten…

The paper introduces SafeRedirect, a system-level defense that prevents frontier LLMs from generating harmful content during legitimate tasks that structurally require it, significantly reducing unsaf…

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 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…

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 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 conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…