The proposed Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance, achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large language models, and SR approaches.
Abstract
While symbolic regression (SR) has been successfully used in science to discover new equations, its use in financial valuation is hindered by several limitations. Whereas the natural sciences provide objectively correct relationships, financial valuation constitutes a distinct class of symbolic discovery problems, as it admits multiple valid perspectives, operates under non-stationary market conditions, and involves noisy, continuous performance signals. In this work, we propose Multi-Agent Fundamental Analysis with Symbolic Adaptive learning (MUFASA), a hierarchical multi-agent framework for symbolic discovery in finance. MUFASA introduces (1) disentangled equation discovery via specialized agents representing distinct valuation perspectives, (2) a meta-coordinator that performs hierarchical-level reasoning over market context information, and (3) a memory mechanism that reasons over statistical performance summaries (e.g., accuracy, stability, and tail risk) to guide learning under noisy feedback. Experiments across datasets from multiple countries show that MUFASA achieves state-of-the-art performance on the valuation task compared to classical finance methods, financial large language models, and SR approaches, while simultaneously producing interpretable equations, which we share with the community. We also make publicly available the distilled learnings across evolution iterations and context-dependent strategy weights, which might offer useful insights for future research on financial fundamental analysis.
Price-direction prediction has long been treated as the central task in building automated trading systems. What such systems rarely address is whether a proposed trade makes economic sense, sits within an acceptable risk envelope, or can be justified to a human analyst. This paper presents NeSy-MAT (Neuro-Symbolic Mul...
P. P. Adhikari, Vineeta Khemchandani, Neetu Sharma· International journal of com...· 0 citations
This paper introduces IdeaSearchFitter, a framework that employs Large Language Models (LLMs) as semantic operators within an evolutionary search that achieves competitive, noise-robust performance on the Feynman Symbolic Regression Database (FSReD), outperforming several strong baselines.
Zhuo-Yang Song, Ze-Yu Cai, Shu-Tao Zhang et al.· Communications in Theoretica...· 0 citations
This work introduces META (Memory Enhanced Trading Agent), the first RAG-like episodic-memory-augmented multi-agent framework for financial decision making and demonstrates that episodic memory provides a powerful mechanism for regime-aware, interpretable, and low-latency decision-making in trading and decision making.
Nuo-Yue Xu, Jiang Liu, Wen-Xuan Huang et al.· 0 citations
A reinforcement learning framework that extracts sequential information solely from technical indicator histories, specifically targeting the additional information that static rules might ignore, proves that historical trajectories in technical indicators contain exploitable information that enhances trading performan...
Tomasz Witkowski, Tomasz Wachowicz, Krzysztof Kania· Decision· 0 citations
GoAnt is introduced, a quality-diversity multi-agent search framework that combines non-communicating Explorer, Exploiter and Connector workers with a shared adaptive Mental Map and a compact Queen dispatcher, and a map-independent effective-yield protocol that counts high-quality, mutually nonredundant factors directl...
ICMAPE converts the fixed-confidence identification objective into a reward derived from inference confidence, so that standard reinforcement learning machinery can be applied to decentralized pure exploration.
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.