作者位次 #3/6ACL 2026Poster· Natural Language Processing
Explicit Trait Inference for Multi-Agent Coordination
Suhaib Abdurahman · Etsuko Ishii · Katerina Margatina · Divya Bhargavi · Monica Sunkara · Yi Zhang
摘要
LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misaligned behaviors. We propose Explicit Trait Inference (ETI), a psychologically grounded method for improving coordination. ETI enables agents to...