EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation
Yunbo Long, Yuhan Liu, Alexandra Brintrup
TL;DR
EQ-Negotiator enables edge-deployable small language models to perform credit negotiation with dynamic emotional intelligence by integrating online emotion recognition, a hidden Markov model of emotional strategies, and a game-theoretic WSLS framework. The approach allows 7B-scale models to close the performance gap with larger models while maintaining privacy and low latency. Across diverse debtor behaviors and adversarial tactics, EQ-Negotiator improves debt recovery, negotiation speed, and ethical behavior, highlighting that strategic emotional intelligence, not mere scale, drives success in automated negotiation. This work thus establishes a practical, privacy-preserving path for deploying capable AI negotiators on edge devices in finance and other sensitive domains.
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.