#cost-reduction2 articles

2 articles

AIBullisharXiv – CS AI · 4h ago3

🧠

RUMAD: Reinforcement-Unifying Multi-Agent Debate

Researchers introduce RUMAD, a reinforcement learning framework that optimizes multi-agent AI debate systems by dynamically controlling communication topology. The system achieves over 80% reduction in computational costs while improving reasoning accuracy across benchmark tests, with strong generalization capabilities across different task domains.

AIBullisharXiv – CS AI · 4h ago5

🧠

Democratizing GraphRAG: Linear, CPU-Only Graph Retrieval for Multi-Hop QA

Researchers present SPRIG, a CPU-only GraphRAG system that eliminates expensive LLM-based graph construction and GPU requirements for multi-hop question answering. The system uses lightweight NER-driven co-occurrence graphs with Personalized PageRank, achieving comparable performance while reducing computational costs by 28%.