2 papers
cs.LG2026
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Yi Duan, Ying Liu, Zirui Tang +32
Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improveme…
cs.AI2026
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
Koutian Wu, Junjie Zhou, Ergan Shang +5
Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark datasets and code, and understan…