Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published 6 days ago • 87
When Models Outthink Their Safety: Mitigating Self-Jailbreak in Large Reasoning Models with Chain-of-Guardrails Paper • 2510.21285 • Published Oct 24, 2025 • 4