AI Paper Atlas

Research map / Large language models / Agents, code and math

GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

Hao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang, Chao Zhang, Suyuchen Wang, Qixin Zhang, Zhengyuan Dong, Joao Monteiro, Bang Liu, Qiuzhuang Sun, Tianshu Yu

ICLR 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use reasoning model Qwen-3 (8B) instead of Qwen-2.5 (7B)Qwen · GraphOmni BFS order (Hard)accuracy (%): 1.38 -> 29.53Improved
scale Qwen-2.5 from 7B to 72BQwen-2.5 · GraphOmni BFS order (Easy)accuracy (%): 21.46 -> 71.41Improved
scale Qwen-2.5 from 7B to 72BQwen-2.5 · GraphOmni Triangle (Hard)accuracy (%): 4.45 -> 4.73No clear effect
use Qwen-3 (8B) instead of Qwen-2.5 (72B)Qwen · GraphOmni Triangle (Hard)accuracy (%): 4.73 -> 19.54Improved
raise difficulty from Easy to Hardo4-mini · GraphOmni BFS orderaccuracy (%): 95.46 -> 32.45Hurt
raise difficulty from Easy to Hardo4-mini · GraphOmni Triangleaccuracy (%): 84.54 -> 17.53Hurt
add algorithm-based promptsLLMs · GraphOmni BFS order and DiameteraccuracyImproved
add multi-shot exemplars to promptopen-source models · GraphOmni (avg over tasks)accuracyImproved
add multi-shot exemplars to promptclosed-source models · GraphOmni (avg over tasks)accuracyNo clear effect
vary serialization format and prompt schemeGPT-4o · GraphOmni (single task)accuracy: gaps of up to 40%Mixed
increase graph size to 30-50 nodesLLMs · GraphOmni BFS order and TriangleaccuracyHurt
increase graph size to 30-50 nodesLLMs · GraphOmni Connectivity and CycleaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy