Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems

2026-05-23

AI Summary

Existing multi-agent large language model (LLM) portfolio systems suffer from ineffective credit assignment, vulnerability to cold-start issues under market regime shifts, and low decision transparency. This work proposes the Market Regime Committee (MRC) framework, which pioneers the application of Shapley values to multi-agent LLM-based financial decision-making by dynamically weighting agents based on precise contributions of individual agents, pairwise coalitions, and the grand coalition. Enhanced with Bayesian adaptive ensembling, state-dependent multiplier optimization, and a five-layer causal tracing mechanism, MRC significantly improves both interpretability and robustness. Evaluated across 13 crypto assets over 1,037 trading days, the system achieves a cumulative return of 440.1% and a Sharpe ratio of 1.51, with the lowest maximum drawdown among all active strategies, comprehensively outperforming established benchmarks.

Abstract

Multi-agent LLM decision systems for portfolio management still lack a principled way to assign credit across specialist agents, remain vulnerable to cold-start dominance under regime shifts, and offer limited transparency into how final allocations are formed. We propose Market Regime Council (MRC), a cooperative multi-agent decision system that computes exact Shapley credits across all single, pairwise, and Grand-coalition outputs for online agent weighting. Instantiated with N=3 specialist agents, at each trading period, MRC recomputes coalition-based Shapley weights from exponentially weighted performance histories, uses a Bayesian adaptive mixture to stabilize early periods, applies regime-dependent multipliers to adjust agent authority, and records each rebalance through a five-layer causal trace. Over 1,037 trading days across 13 crypto assets and five seeds, MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1%, ranking first on CR, SR, and IR among active baselines and attaining the lowest MDD among active methods. Ablation results show that the gains come from Shapley-weighted integration across coalition outputs rather than from any single stage in isolation. Code and demo data are included in the supplementary material.

Problem

• credit assignment
• market regime shifts
• multi-agent LLM
• transparency
• portfolio management

Innovation

• Shapley credit assignment
• multi-agent LLM
• market regime adaptation
• dynamic agent weighting
• causal traceability