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

2025-11-05

AI Summary

Small language models (SLMs) deployed on privacy-sensitive edge devices exhibit insufficient emotional intelligence for credit negotiation tasks. Method: We propose a Dynamic Emotional Role Modeling framework that enables online, pretraining-free emotional state tracking and explicitly integrates emotional intelligence into SLM inference. By unifying game-theoretic reasoning with lightweight hidden Markov models, our approach realizes real-time emotion inference and adaptive adversarial strategy generation. Contribution/Results: Our method bridges the emotional intelligence gap between SLMs and large language models (LLMs), enabling a 7B-parameter model to outperform LLMs ten times its size in debt recovery rate and negotiation efficiency. Empirical results demonstrate that strategic emotional intelligence—not parameter count—is the decisive factor for negotiation performance. The framework establishes a new paradigm for edge-native AI negotiation systems that are energy-efficient, privacy-preserving, and ethically grounded.

Technology Category

• Humans and AI: Emotional Intelligence
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Natural Language Processing: Safety and Robustness

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Bridging performance gap between small and large language models in negotiation
• Enabling emotionally intelligent negotiation within privacy constraints for edge devices
• Countering manipulation tactics while maintaining ethical standards in credit negotiations

Innovation

• Integrates game theory with Hidden Markov Model
• Learns debtor emotional states online without pre-training
• Enables small models to outperform larger language models