GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning

ArXi:2605.06671v1 Announce Type: new Large Language Models (LLMs) have nstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since graphs are naturally complex in topology and often require systematic multi-step reasoning, especially on larger graphs. Motivated by this gap, we propose GraphDC, a Divide-and-Conquer multi-agent framework for scalable graph algorithm reasoning.