A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, et al.
SCoRe is a multi-turn online RL method that significantly improves LLM self-correction using only self-generated data, achieving state-of-the-art gains on MATH and HumanEval.
Unknown
Proposes an Agentic Graph RAG framework with self-correction for clinical decision support in hepatology, outperforming GPT-4, standard RAG, and Graph RAG.
Beichen Zhang, Yuhang Zang, Xiao-wen Dong, et al.
Proposes Vision-Language Synergy Reasoning (VLSR) and Modality-Switch Self-Correction (MSSC) to improve abstract reasoning on ARC-AGI by combining visual abstraction with linguistic reasoning.
Binjie Zhang, M. Shou
ReGRPO enhances tool-using agents by integrating reflection-guided correction into policy optimization, improving performance through iterative self-correction.