LLMs with Personalities in Multi-issue Negotiation Games

arXiv:2405.05248v1 Announce Type: new
Abstract: Powered by large language models (LLMs), AI agents have become capable of many human tasks. Using the most canonical definitions of the Big Five personality, we measure the ability of LLMs to negotiate within a game-theoretical framework, as well as methodological challenges to measuring notions of fairness and risk. Simulations (n=1,500) for both single-issue and multi-issue negotiation reveal increase in domain complexity with asymmetric issue valuations improve agreement rates but decrease surplus from aggressive negotiation. …

abstract agents ai agents arxiv become big canonical challenges cs.ai cs.cl cs.ma definitions fairness five framework game games human issue language language models large language large language models llms measuring negotiation personalities personality tasks type