ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding

Z Sun, Q Wang, W Yu, X Zang, K Zheng, J Xu… - arxiv preprint arxiv …, 2025 - arxiv.org
Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold
promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning …

ProgCo: Program Helps Self-Correction of Large Language Models

X Song, Y Wu, W Wang, J Liu, W Su… - arxiv preprint arxiv …, 2025 - arxiv.org
Self-Correction aims to enable large language models (LLMs) to self-verify and self-refine
their initial responses without external feedback. However, LLMs often fail to effectively self …