2 papers
cs.CL2026
The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization
Chengxiao Dai, Zhaokun Yan, Zhanhui Lin
Headline type-correctness (TC\%) of LLM autoformalization has climbed from 53\% to 76\% in two years, yet this scalar conceals which errors each method resolves. We pro…
cs.AI2025
aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists
Pengsong Zhang, Xiang Hu, Guowei Huang +20
Recent advances in large language models (LLMs) have enabled AI agents to autonomously generate scientific proposals, conduct experiments, author papers, and perform peer reviews.…