GoAnt improves discovery of trading signals from market data by balancing search methods
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstructure Data
Artificial Intelligence
Summary
Finding good trading signals automatically is hard because many attempts repeat the same ideas or fail when real costs are considered. The authors present GoAnt, a system that uses different types of search agents working together but independently to explore a wide variety of trading signals more effectively. GoAnt keeps track of the best unique signals and smartly manages its efforts to find new valuable ones. Tests on real stock market data show GoAnt finds better, more diverse signals than previous methods and keeps most of its success when tested on new data.
alpha factorsmarket microstructuresymbolic regressionquality-diversity searchmulti-agent systemsexecution costsprice-volume dataorder-book dataoverfittingevaluation budget
Authors
Stella Zhao, Tommy Sha
Abstract
Automated alpha factor discovery searches symbolic trading signals from price-volume panels and order-book data under a fixed evaluation budget. Existing single- and multi-agent program-search systems can overfit predictive proxies that fail after execution costs and repeatedly explore redundant factor families, limiting execution robustness and behavioral diversity. We introduce GoAnt, 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. The Mental Map organizes candidates by leakage-free execution profiles and retains one elite per niche, while the Queen reallocates the evaluation budget from explicit search-state summaries. We also define a map-independent effective-yield protocol that counts high-quality, mutually nonredundant factors directly from each method's evaluation records, giving archive-based and map-free systems the same ruler. On real A-share microstructure data spanning 2023--2026, GoAnt reaches quality-weighted yields of 41.8 and 47.6 in price-volume and order-book settings, improving the strongest baseline by 57% and 97% under matched budgets. Its locked populations retain 0.64 and 0.67 of in-sample quality out of sample, compared with 0.61 and 0.63 for a static map.