AgreeMate: Teaching LLMs to Haggle

TL;DR

AgreeMate is a framework that trains large language models to conduct strategic price negotiations using natural language, leveraging prompt engineering and fine-tuning to improve performance in bargaining tasks.

Contribution

The paper introduces a novel approach for training LLMs in negotiation settings, combining prompt engineering, fine-tuning, and attention analysis to enhance bargaining capabilities.

Findings

Prompt engineering and fine-tuning improve negotiation performance.

Attention probing reveals semantic understanding during bargaining.

LLMs can effectively perform strategic negotiations with proper training.

Abstract

We introduce AgreeMate, a framework for training Large Language Models (LLMs) to perform strategic price negotiations through natural language. We apply recent advances to a negotiation setting where two agents (i.e. buyer or seller) use natural language to bargain on goods using coarse actions. Specifically, we present the performance of Large Language Models when used as agents within a decoupled (modular) bargaining architecture. We demonstrate that using prompt engineering, fine-tuning, and chain-of-thought prompting enhances model performance, as defined by novel metrics. We use attention probing to show model attention to semantic relationships between tokens during negotiations.