CLIFER：通过持续学习实现人机智能体谈判中的个性化情感感知

View PDF HTML (experimental)

Abstract:Self-interested intelligent agents that negotiate with humans should interpret nonverbal expressions and adapt their behavior accordingly. However, generic facial-affect models degrade across individuals and contexts, creating a generalization gap. We introduce an affect-adaptive negotiation strategy that incorporates Continual Learning with Imagination for Facial Expression Recognition (CLIFER) to personalize valence-arousal perception in real time. Differential feedback converts changes in valence-arousal direction and intensity into adjustments of the agent's target utility. An asynchronous architecture updates CLIFER in the background during live interaction. In a counterbalanced within-subject study in which 66 participants negotiated with a humanoid robot, the CL-enabled agent achieved significantly higher individual utility and elicited higher participant concession rates than the FaceChannel baseline. The CL condition yielded significantly higher mean arousal estimates, alongside a broader output range. Participant utility and Nash distance did not change significantly between conditions. These outcomes support the practical value of coupling continual affective personalization with differential feedback for real-time negotiation.

Comments:	17 pages, 11 figures. Submitted to IEEE Transactions on Affective Computing
Subjects:	Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC); Machine Learning (cs.LG); Multiagent Systems (cs.MA); Robotics (cs.RO)
MSC classes:	68T05, 91A10, 91B26
ACM classes:	I.2.11; H.1.2; I.2.7; I.2.6
Report number:	TAFFC-2026-05-0739
Cite as:	arXiv:2611.14247 [cs.AI]
	(or arXiv:2611.14247v1 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2611.14247 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mehmet Onur Keskin [view email]
[v1] Tue, 10 Nov 2026 15:57:45 UTC (30,184 KB)