作者位次 #7/15ACL 2026Poster· Natural Language Processing
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
Yuhang Zhou · Mingrui Zhang · Ke Li · Mingyi Wang · Qiao Liu · Qifei wang · Jiayi Liu · Fei Liu · Serena Li · Weiwei LI · Mingze Gao · Abhishek Kumar · Xiangjun Fan · Zhuokai Zhao · Lizhu Zhang
摘要
Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approaches remain limited. Fine-tuning based methods strengthen language reasoning; yet they are prone to arithmetic errors...