ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving Paper • 2607.00466 • Published 9 days ago • 31
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources Paper • 2605.29250 • Published May 28 • 80
Adaptive Multi-Agent Response Refinement in Conversational Systems Paper • 2511.08319 • Published Nov 11, 2025 • 42
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs Paper • 2510.07499 • Published Oct 8, 2025 • 49
UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities Paper • 2504.20734 • Published Apr 29, 2025 • 62