CompEvo: Competition-Induced Evolution for Multi-Agent in News-Driven Time Series Forecasting

2026-09-02

AI Summary

为解决多智能体新闻驱动时间序列预测中的思维退化和理论基础不足问题，提出CompEvo框架，通过竞争诱导演化提升多样性和准确性。

Abstract

News-driven time series forecasting uses evolving textual events together with historical observations to predict future values, supporting applications such as market risk monitoring and resource scheduling. In multi-agent settings, two challenges still remain. The first is degeneration of thought, where agents converge to similar evidence-seeking behaviors. The second is insufficient theoretical grounding, where strategy updates are often heuristic and lack a principled formulation. To address the above challenges, we propose CompEvo, a competition-induced evolution framework for multi-agent news-driven time series forecasting. For theoretical grounding, we introduce an evolutionary game formulation to guarantee equilibrium existence and optimization convergence. Building on this formulation, we construct a trainable multi-agent evolution framework that integrates strategy execution, fitness-based differentiable selection, and competition-induced strategy evolution. CompEvo enables heterogeneous agents to explore diverse news evidence, converts forecasting feedback into differentiable influence weights, and evolves agent strategies under competitive pressure to preserve effective logic while maintaining diversity. Experiments on four real-world datasets show that CompEvo reduces RMSE by 27.3% and MAPE by 26.2% on average over strong baselines. Further analysis indicates that CompEvo successfully maintains diverse and specialized agent behaviors.

Problem

• multi-agent
• news-driven time series forecasting
• degeneration of thought
• theoretical grounding

Innovation

• Evolutionary Game
• Multi-Agent Evolution
• News-Driven Time Series Forecasting
• Differential Selection
• Competitive Strategy Evolution