Negotiating With A Human-Like Ai Agent

Authors:

Abstract: The idea of merging negotiation and AI has been a dream for many decades, which has inspired research on negotiation and different AI technologies (machine learning, deep learning, computer vision, natural language processing, and even robotics). In attempts to emulate negotiation behavior or improve performance, researchers and entrepreneurs explored different AI systems, including rule-based systems, predictive analytics, generative models, autonomous systems to create support systems or virtual agents that can help us perform as well or better than human negotiators alone. After the awe or jump scare most people felt following the ChatGPT launch on November 30, 2022, large language models (LLMs) popularized AI and opened people's imagination to how machines can become a part of negotiations. LLMs revolutionized our perception and adoption of AI with their user-friendliness and ability to engage in undistinguishable human-like, fluent, and multi-topic conversations, though relatively few LLM applications exist for competitive or mixed-motive settings, namely negotiations. Besides, given the opaqueness of their reasoning processes and outputs, as well as their many challenges and weaknesses (prompt hacks, biases, skill gaps, ethical and reasoning deficits, etc), there is still much work to be done before such AI-powered agents can become truly autonomous human-like negotiators. We will invite participants to role-play with out our LLM-powered negotiation agent, developed for educational purposes, and then explain our efforts to enable a realistic and human-like negotiation experience as we leverage AI to power the avatar with personality, cultural, and emotional dimensions.

Track: TEACH

Keywords: Negotiation, Conflict Management, AI-powered agent, Role-play simulation