Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiangchao Yan

Xiangchao Yan

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

AI×3NLP×1

Frequent co-authors

Yifan Zhou2×
Wenlong Zhang2×
Zongsheng Cao2×
Jinxin Shi2×
Tianshuo Peng2×
Shiyang Feng2×

Research Timeline

2026
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

Agents-K1: Towards Agent-native Knowledge Orchestration

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

The paper introduces IdeaGene-Bench, a benchmark for scientific lineage reasoning and idea generation, which includes 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise GenomeDiff records.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentJul 9, 2026

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

Yifan Zhou, Qihao Yang, Yan Li, Donggang Li +13 more

The paper introduces IdeaGene-Bench, a benchmark for scientific lineage reasoning and idea generation, which includes 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise G…

View →
cs.AIEmpiricalRecent
Jun 11, 2026

Agents-K1: Towards Agent-native Knowledge Orchestration

Zongsheng Cao, Bihao Zhan, Jinxin Shi, Jiong Wang +21 more

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.

View →
cs.AIcs.CLRecentJun 4, 2026

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery

Shangheng Du, Xiangchao Yan, Jinxin Shi, Zongsheng Cao +10 more

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

View →