ACE: A LLM-based Negotiation Coaching System
Ryan Shea, Aymen Kallala, Xin Lucy Liu, Michael W. Morris, Zhou Yu
TL;DR
ACE tackles the accessibility gap in negotiation training by deploying an LLM-based coaching assistant that combines a curriculum-informed annotation scheme with targeted preparation and negotiation feedback. Built on a dataset of MBA negotiation transcripts, ACE identifies user mistakes and provides actionable guidance through both turn-based and holistic feedback, guided by dynamic prompting and a robust negotiation agent. Large-scale user studies show that ACE significantly enhances both objective negotiation outcomes and subjective learning metrics compared with no feedback and alternative feedback methods. This work advances democratized, curriculum-aligned negotiation education and offers a framework for feedback-driven negotiation tutoring using LLMs.
Abstract
The growing prominence of LLMs has led to an increase in the development of AI tutoring systems. These systems are crucial in providing underrepresented populations with improved access to valuable education. One important area of education that is unavailable to many learners is strategic bargaining related to negotiation. To address this, we develop a LLM-based Assistant for Coaching nEgotiation (ACE). ACE not only serves as a negotiation partner for users but also provides them with targeted feedback for improvement. To build our system, we collect a dataset of negotiation transcripts between MBA students. These transcripts come from trained negotiators and emulate realistic bargaining scenarios. We use the dataset, along with expert consultations, to design an annotation scheme for detecting negotiation mistakes. ACE employs this scheme to identify mistakes and provide targeted feedback to users. To test the effectiveness of ACE-generated feedback, we conducted a user experiment with two consecutive trials of negotiation and found that it improves negotiation performances significantly compared to a system that doesn't provide feedback and one which uses an alternative method of providing feedback.