The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning

Yafu Li, Zhilin Wang, Tingchen Fu, Ganqu Cui, Sen Yang 0005, Yu Cheng 0001. The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 31369-31389, Association for Computational Linguistics, 2026. [doi]

Abstract

Abstract is missing.