Bridging Semantics and Strategy: A Dual-Stream Graph Network for Equitable Negotiation Forecasting

2026-05-28

AI Summary

Existing hybrid-motivation negotiation prediction models struggle to effectively integrate linguistic semantics with implicit strategic constraints—such as budget limits and alternative options—and often overlook historical fairness in resource allocation, resulting in limited cross-task generalization. To address these limitations, this work proposes a Semantic–Temporal Graph Fusion Network (ST-GFN) featuring a dual-stream architecture: one stream employs Transformers to encode dialogue text, while the other leverages graph attention networks to model economic states. A dynamic gating mechanism adaptively fuses these multimodal signals, and a fairness-aware regularization loss is introduced to constrain utility disparities. Evaluated on the DealOrNoDeal and CaSiNo benchmarks, the proposed method reduces inequality bias by 43.8% in high-disparity scenarios with negligible accuracy trade-offs and demonstrates superior robustness in high-variance environments.

Abstract

Forecasting outcomes in mixed-motive negotiations requires integrating explicit linguistic cues with latent strategic constraints, such as budgets and alternatives. Existing computational models often fail to adapt to varying task structures and may not adequately account for distributive considerations present in historical training data. This study proposes a unified framework to adaptively fuse semantic and strategic signals while incorporating reflective modeling of utility disparities. We introduce the Semantic-Temporal Graph Fusion Network (ST-GFN), a dual-stream architecture that processes textual dialogue with transformer encoders and economic states with Graph Attention Networks, connected via a dynamic gated fusion mechanism. Evaluated on contrasting benchmarks, the linguistically oriented DealOrNoDeal and the strategy-oriented CaSiNo, ST-GFN exhibits strong adaptability. The model dynamically adjusts modality weighting, emphasizing linguistic cues in free-form settings (z ~ 0.97) and increasing reliance on strategic constraints in structured tasks (z ~ 0.73). A fairness-regularized composite loss is incorporated to penalize deviations from ground-truth utility gaps. Results demonstrate a 43.8% reduction in Inequality Discrepancy in high-disparity environments with minimal impact on accuracy, alongside improved performance in high-variance domains. These findings suggest that reflective regularization can enhance both predictive reliability and equitable representation in negotiation forecasting, supporting the design of transparent Group Decision and Negotiation Support Systems (GDNSS).

Problem

• negotiation forecasting
• semantic-strategic integration
• utility disparity
• fairness
• mixed-motive negotiation

Innovation

• dual-stream architecture
• dynamic gated fusion
• fairness-regularized loss
• Graph Attention Networks
• negotiation forecasting