Papers2

#HotpotQA

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Hyesung Jeon, Hyeongju Ha et al.Feb 1arXiv

Multi-agent LLM systems often use LoRA adapters so each agent has a special role, but they all rebuild almost the same KV cache, wasting memory and time.

#LoRA#Multi-LoRA#KV cache

FABLE: Forest-Based Adaptive Bi-Path LLM-Enhanced Retrieval for Multi-Document Reasoning

Intermediate

Lin Sun, Linglin Zhang et al.Jan 26arXiv

FABLE is a new retrieval system that helps AI find and combine facts from many documents by letting the AI both organize the library and choose the right shelves to read.

#FABLE#Structured RAG#Hierarchical retrieval