5 papers
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.…
Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic
Yang Yan, Yu Lu, Renjun Xu +1
Large language models (LLMs) achieve impressive results on advanced mathematics benchmarks but sometimes fail on basic arithmetic tasks, raising the question of whether they have t…
Value Residual Learning
Zhanchao Zhou, Tianyi Wu, Zhiyun Jiang +2
While Transformer models have achieved remarkable success in various domains, the effectiveness of information propagation through deep networks remains a critical challenge. Stand…
QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
Zijie Chen, Zhanchao Zhou, Yu Lu +3
Solving NP-hard problems traditionally relies on heuristics, yet manually designing effective heuristics for complex problems remains a significant challenge. While recent advancem…
Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas
Xiang Hu, Hongyu Fu, Jinge Wang +7
Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produc…