KCoT reframes CoT graph learning as k-means clustering by establishing a formal correspondence between Transformer blocks and k-means assignment/update steps, with a Semantic Discriminating Prompt and structure alignment yielding gains on benchmarks.
Evaluating large language models on graphs: Perfor- mance insights and comparative analysis,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
GraphDC applies divide-and-conquer multi-agent LLM reasoning to graph algorithms by decomposing graphs into subgraphs for local agents and integrating via a master agent, outperforming direct methods especially on large scales.
LLM-generated waypoints guided by landmark distances reduce A* node expansions by ~50% in non-geometric graphs up to 2000 nodes with only marginal path cost increase.
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.
citing papers explorer
-
Clustering as Reasoning: A $k$-Means Interpretation of Chain-of-Thought Graph Learning
KCoT reframes CoT graph learning as k-means clustering by establishing a formal correspondence between Transformer blocks and k-means assignment/update steps, with a Semantic Discriminating Prompt and structure alignment yielding gains on benchmarks.
-
GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
GraphDC applies divide-and-conquer multi-agent LLM reasoning to graph algorithms by decomposing graphs into subgraphs for local agents and integrating via a master agent, outperforming direct methods especially on large scales.
-
LLM-Aided A* Search in Non-Geometric Network Graphs
LLM-generated waypoints guided by landmark distances reduce A* node expansions by ~50% in non-geometric graphs up to 2000 nodes with only marginal path cost increase.
-
Are Large Language Models Suitable for Graph Computation? Progress and Prospects
A survey of LLMs for graph computation introduces a role-based taxonomy of executors versus planners and concludes that current models suit simple small-scale tasks but remain unreliable for large-scale exact computation.