Jun He

The paper introduces Argus, a novel multi-agent framework that reorchestrates Static Application Security Testing (SAST) by integrating LLMs with existing tools to achieve superior, reliable, and cost-effective vulnerability detection.

The paper introduces Sovereign Agentic Loops (SAL), a control-plane architecture that decouples LLM reasoning from system execution to enhance safety and reliability in real-world AI agents.

The paper introduces Post-Deterministic Distributed Systems (PDDS) as a new model to coordinate autonomous infrastructure where participants, including stochastic agents, produce divergent reasoning paths while achieving correct, semantically equivalent outcomes.

The paper introduces Post-Deterministic Distributed Systems (PDDS) as a new model to coordinate autonomous infrastructure where participants, including stochastic agents, produce divergent reasoning paths while achieving correct, semantically equivalent outcomes.

This paper introduces the Sovereign Assurance Boundary (SAB), a certificate-bound runtime admission layer for autonomous execution authority.

This paper introduces the Sovereign Execution Broker (SEB), a runtime enforcement boundary for certificate-bound agentic infrastructure.

This paper introduces Epistemic Byzantine Fault Tolerance (EBFT), a fault-tolerance model for agentic infrastructure and post-deterministic distributed systems, addressing the Honest Quorum Problem and its impact on semantic safety and liveness.

This paper proposes SynPre-FL, a framework that combines high-fidelity synthetic EHR generation with federated learning for robust clinical prediction.

KedgeFlow specifies language-independent contracts for trusted controllers to authorize state-changing operations and privileged gateways to enforce that authority independently of agent reasoning.