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 PassNet, a large-scale ecosystem for generating compiler passes using LLMs, demonstrating that LLMs can significantly accelerate graph compilation for long-tail workloads, suggesting that consistency is the primary bottleneck.

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.