Tag
RAIL Guard is a closed-loop pipeline that evaluates LLM outputs across eight responsible AI dimensions and iteratively remediates failures, achieving 96.9% convergence vs 49.1% for block-and-retry, with open-source SDKs.
Devin Cloud launches Security Swarm, using Agentic MapReduce to find security vulnerabilities in codebases, with remediation and fleet management in the Desktop app.
PropGuard is a propagation-aware framework for safeguarding LLM-based multi-agent systems (LLM-MAS) from malicious instructions that propagate across agents and rounds. It constructs a dual-view spatio-temporal graph and uses a GE-GRPO trained inspector to detect and remediate suspicious propagation subgraphs.