AI RESEARCH
GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs
arXiv CS.CL
•
ArXi:2604.23626v1 Announce Type: new LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to realistic and challenging applications, routing must extend into agentic LLM settings, where task planning, multi-round cooperation among heterogeneous agents, and memory utilization are indispensable.