MRC：多智能体 LLM 决策系统中的市场状态动态信用分配机制

View PDF HTML (experimental)

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), an online credit-assignment mechanism over coalitions of specialist agents, with portfolio management as the downstream task. MRC 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 available open source.

Comments:	40 pages, 13 figures. Accepted author manuscript, NeurIPS 2026 (Main Track). Code and demo data available open source
Subjects:	Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Portfolio Management (q-fin.PM)
Cite as:	arXiv:2605.24490 [cs.AI]
	(or arXiv:2605.24490v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2605.24490 arXiv-issued DOI via DataCite

Submission history

From: John Cartlidge [view email]
[v1] Sat, 23 May 2026 09:41:52 UTC (9,485 KB)
[v2] Tue, 10 Nov 2026 11:13:13 UTC (9,502 KB)