一作AAAI 2026Poster· Artificial Intelligence
Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning
Wenda Wei · Yu-An Liu · Ruqing Zhang · Jiafeng Guo · Lixin Su · Shuaiqiang Wang · Dawei Yin · Sebastian Schelter · Xueqi Cheng