3 papers
cs.AI2026
Manalyzer: End-to-end Automated Meta-analysis with Multi-agent System
Wanghan Xu, Wenlong Zhang, Fenghua Ling +8
Meta-analysis is a systematic research methodology that synthesizes data from multiple existing studies to derive comprehensive conclusions. This approach not only mitigates limita…
cs.AI2025
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Wanghan Xu, Yuhao Zhou, Yifan Zhou +104
Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…
cs.CL2025
ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning
Hongwei Liu, Junnan Liu, Shudong Liu +33
The rapid advancement of Large Language Models (LLMs) has led to performance saturation on many established benchmarks, questioning their ability to distinguish frontier models. Co…