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

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 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 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 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…

EvoPoC introduces a knowledge-driven agentic system that automates the synthesis of verifiable and economically viable exploits for DeFi smart contracts, achieving high recall and significant revenue…

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 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 argues that current Software Bills of Materials (SBOMs) are fundamentally flawed due to a lack of shared understanding regarding what constitutes a 'component,' demonstrating that existing t…

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…

The paper introduces the concepts of Agentic Technical Debt and Stochastic Tax to categorize and manage the unique governance and operating liabilities inherent in complex, multi-step AI agent systems…

The paper provides a mechanized proof in Isabelle/HOL guaranteeing both the safety (state preservation) and liveness (progress) of regulatory state transitions across multiple, heterogeneous blockchai…

This paper analyzes the UK Cyber Security and Resilience Bill, arguing that its comprehensive provisions necessitate a shift away from perimeter-based security models toward a Zero Trust Architecture…

The paper introduces MEV non-interference, a formal security notion, to ensure that composing new smart contracts in DeFi does not increase the maximal extractable value, thereby providing a formal fo…

The paper introduces the Lean-Agent Protocol, a formal verification platform that uses Lean 4 theorem proving to ensure agentic AI actions in finance are mathematically compliant with complex regulati…

The paper proposes a novel nine-dimension risk assessment framework for institutional DeFi adoption, significantly enhancing existing methodologies by incorporating novel dimensions like composability…

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…