Can Competition Enhance the Proficiency of Agents Powered by Large Language Models in the Realm of News-driven Time Series Forecasting?
This work addresses the problem of improving forecasting accuracy in multi-agent systems for researchers and practitioners in AI and finance, though it is incremental as it builds on existing multi-agent frameworks.
The study tackled the challenge of enhancing multi-agent systems for news-driven time series forecasting by embedding a competition mechanism to boost innovative thinking and using a fine-tuned small-scale LLM to improve identification of misleading information, resulting in significant performance improvements in time series prediction.
Multi-agents-based news-driven time series forecasting is considered as a potential paradigm shift in the era of large language models (LLMs). The challenge of this task lies in measuring the influences of different news events towards the fluctuations of time series. This requires agents to possess stronger abilities of innovative thinking and the identifying misleading logic. However, the existing multi-agent discussion framework has limited enhancement on time series prediction in terms of optimizing these two capabilities. Inspired by the role of competition in fostering innovation, this study embeds a competition mechanism within the multi-agent discussion to enhance agents' capability of generating innovative thoughts. Furthermore, to bolster the model's proficiency in identifying misleading information, we incorporate a fine-tuned small-scale LLM model within the reflective stage, offering auxiliary decision-making support. Experimental results confirm that the competition can boost agents' capacity for innovative thinking, which can significantly improve the performances of time series prediction. Similar to the findings of social science, the intensity of competition within this framework can influence the performances of agents, providing a new perspective for studying LLMs-based multi-agent systems.