EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation

TL;DR

EQ-Negotiator enables small language models to perform emotionally aware credit negotiations by dynamically tracking debtor emotions, achieving competitive results with much larger models while preserving privacy and ethical standards.

Contribution

Introduces a novel emotional persona framework for small language models using game theory and HMMs, enhancing negotiation capabilities without pre-training.

Findings

7B model with EQ-Negotiator outperforms larger LLMs in debt recovery

Dynamic emotional modeling improves negotiation efficiency

Strategic emotional intelligence surpasses raw model scale

Abstract

The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.