FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution

TL;DR

FinEvo reframes financial strategy evaluation as an ecological game, where heterogeneous trading agents co-evolve under an endogenous price-formation process. It introduces a FinEvo SDE that combines selection, innovation, and environmental perturbation to capture population-level adaptation and emergent market dynamics, with theoretical guarantees on simplex invariance and existence of invariant measures. Through artificial shocks and real-world news scenarios, FinEvo reveals context-dependent outcomes, coalition dynamics, and regime shifts that static backtests miss, while reproducing stylized facts such as fat tails and volatility clustering. The framework provides a principled platform for studying robustness, market design, and regulatory impacts on price evolution and ecological balance in multi-agent financial markets.

Abstract

Conventional financial strategy evaluation relies on isolated backtests in static environments. Such evaluations assess each policy independently, overlook correlations and interactions, and fail to explain why strategies ultimately persist or vanish in evolving markets. We shift to an ecological perspective, where trading strategies are modeled as adaptive agents that interact and learn within a shared market. Instead of proposing a new strategy, we present FinEvo, an ecological game formalism for studying the evolutionary dynamics of multi-agent financial strategies. At the individual level, heterogeneous ML-based traders-rule-based, deep learning, reinforcement learning, and large language model (LLM) agents-adapt using signals such as historical prices and external news. At the population level, strategy distributions evolve through three designed mechanisms-selection, innovation, and environmental perturbation-capturing the dynamic forces of real markets. Together, these two layers of adaptation link evolutionary game theory with modern learning dynamics, providing a principled environment for studying strategic behavior. Experiments with external shocks and real-world news streams show that FinEvo is both stable for reproducibility and expressive in revealing context-dependent outcomes. Strategies may dominate, collapse, or form coalitions depending on their competitors-patterns invisible to static backtests. By reframing strategy evaluation as an ecological game formalism, FinEvo provides a unified, mechanism-level protocol for analyzing robustness, adaptation, and emergent dynamics in multi-agent financial markets, and may offer a means to explore the potential impact of macroeconomic policies and financial regulations on price evolution and equilibrium.

Figures (18)

• Figure 1: Agent population shares over time. Left: positive shock; Right: negative shock.
• Figure 2: Correlation matrices over time under positive (top) and negative (bottom) shocks. Red = cooperation, Blue = competition.
• Figure 3: Responses under external shocks: Left = positive shock, Right = negative shock. In (b), Blue = selection, Red = innovation, Green = perturbation.
• Figure 4: Intra-day evolution on July 7, 2025: (left) agent population proportions, (middle) theoretical volatility metrics, and (right) cumulative returns under a 0.5% transaction cost (including slippage).
• Figure 5: Dynamic evolution of intra-day correlation matrices on July 7, 2025. Red blocks represent synergistic alliances, while blue blocks indicate strategic antagonism.

Theorems & Definitions (3)

• Lemma 1: Well-posedness
• Proposition 1: Simplex invariance and positivity
• Proposition 2: Invariant measure and quasi-stability