Jie Wu

The paper introduces the concept of policy-invisible violations in LLM agents and proposes Sentinel, a counterfactual graph simulation framework, which significantly improves policy enforcement accuracy by incorporating hidden world-state context.

The paper introduces Distributed Sentinel, a zero-trust architecture that prevents Context-Fragmented Violations (CFVs) in multi-agent systems by propagating security state across departmental boundaries.

The paper introduces FedRAG, a novel federated RAG framework that enables privacy-preserving cross-institutional knowledge collaboration by decoupling the self-attention mechanism from data localization using a specialized scrambling protocol.

The paper introduces $ ext{RLR}^3$, a novel framework that extends verifiable rewards in Reinforcement Learning to handle partially verifiable, multi-criteria vision-language tasks by integrating robust rubric scoring.

MemGraphRAG introduces a novel memory-based multi-agent system to construct globally consistent and structurally sound knowledge graphs, significantly improving retrieval-augmented generation for complex, large-scale corpora.

The paper introduces Temperature-Scaled On-Policy Self-Distillation (TS-OPSD), a novel method that internalizes temperature-based policy reheating into model parameters to combat entropy collapse in reinforcement learning.