graph algorithms

2 items

RESEARCHDEV.to AI·4/28/2026

Ranking via Sinkhorn Propagation

This research introduces a novel approach to ranking using Sinkhorn propagation, a method known for solving optimal transport problems. It explores how this technique can be effectively applied to establish robust and coherent rankings.

ranking Optimization machine learning Sinkhorn Algorithm

RESEARCHarXiv CS.AI·5/11/2026

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

This paper introduces GraphDC, a Divide-and-Conquer multi-agent system designed to enhance graph algorithm reasoning in Large Language Models (LLMs). It improves performance by decomposing large graphs into smaller subgraphs for specialized agents, with a master agent integrating the results, leading to better scalability and robustness.

LLMs scalable AI AI Reasoning multi-agent systems