作者位次 #5/11ACL 2026Findings· Findings of ACL
Preference Estimation via Opponent Modeling in Multi-Agent Negotiation
Yuta Konishi · Kento Yamamoto · Eisuke Sonomoto · Rikuho Takeda · Ryo Furukawa · Yusuke Muraki · Takafumi Shimizu · Kazuma Fukumura · Yuya Kanemoto · Takayuki Ito · Shiyao Ding
摘要
Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete pref...