一作ACL 2026Findings· Findings of ACL
Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models
Can Xu · Lingyong Yan · Jiayi Wu · Haosen Wang · Shuaiqiang Wang · Yuchen Li · Jizhou Huang · Dawei Yin · Xiang Li
摘要
Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-cor...