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

• URL: http://arxiv.org/abs/2605.24490v1
• Date: Sat, 23 May 2026 09:41:52 GMT
• Title: Market Regime Council for Dynamic Credit Assignment in Multi-Agent LLM Decision Systems
• Abstract summary: We propose a cooperative multi-agent decision system that computes exact Shapley credits across all single, pairwise, and Grand-coalition outputs.<n>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%.
• Score: 13.214424787265749
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Sense Once, Serve Many: Common-Trace Factorized Constrained PPO for Online Sensing-Session Consolidation in Multi-Tenant ISAC Networks [0.0]
  We propose Common-Trace Factorized Constrained Proximal Policy Optimization (CT-PPO)<n>CT-PPO achieves the highest mean macro return, exceeding matched Joint-Credit PPO (JC-PPO) by 0.934 and SLA-Aware Greedy by 1.847.<n>A four-way shows that the factorized surrogate alone yields no detectable macro-return gain, whereas adding common-trace reward credit produces the dominant improvement.
  arXiv  Detail & Related papers  (2026-08-29T13:20:21Z)
• F$^2$Agent: Financial Fusion of Agentic Intelligence for Multimodal Trading [24.61485862983447]
  We propose F$2$Agent, a novel agentic paradigm driven by the Financial Fusion of Agentic Intelligence.<n>F$2$Agent first deploys a hierarchy of specialized agents to comprehensively extract modality-specific signals.<n>It further introduces a modality-aware adaptive fusion mechanism and noise-robust consistency regularization to generate noise-resilient trading signals.
  arXiv  Detail & Related papers  (2026-08-06T07:05:17Z)
• ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning [47.96591344642519]
  Multi-Agent Reinforcement Learning requires agents to collectively maximize a shared return.<n>Prior methods largely follow two approaches: independent factorized updates with centralized critics, or alternating best-response updates.<n>We show the joint policy gradient admits an exact decentralized decomposition of per-agent terms, each formed from per-agent score functions and decentralized critics.<n>Central to this result is a serialized view of the simultaneous joint decision in which agents commit actions one at a time, each conditioning on a belief over preceding actions.
  arXiv  Detail & Related papers  (2026-06-29T10:04:15Z)
• CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents [0.9924185669370708]
  We introduce CLQT, which reframes closed-loop trading evaluation as diagnosis rather than ranking.<n> CLQT is a fully closed-loop, cost-aware, strategy-consistent, temporally-gated environment.
  arXiv  Detail & Related papers  (2026-06-29T04:26:30Z)
• Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection [51.90293101535452]
  We propose DMAIC-IAD (DMAIC-inspired Agentic Industrial Anomaly Detection), a "Plan First, Judge Later" multi-agent system.<n>We show DMAIC-IAD improves average detection performance over applicable agentic baselines by 37.76%.
  arXiv  Detail & Related papers  (2026-06-03T08:38:14Z)
• Breaking $\ extit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning [53.42577591449649]
  Group Cooperative Policy Optimization shifts the training paradigm from rollout competition to team cooperation.<n>GCPO replaces independent rollout scoring with team-level credit assignment.<n>It redistributes the collective team reward to each single rollout according to its average marginal contribution to the team.
  arXiv  Detail & Related papers  (2026-05-12T03:20:24Z)
• Signal or Noise in Multi-Agent LLM-based Stock Recommendations? [0.0]
  We present the first portfolio-level validation of MarketSenseAI, a deployed multi-agent LLM equity system.<n>The system routes four specialist agents through a agent that issues a monthly equity thesis and synthesis for each stock in its coverage universe.<n>We ask two questions: do its buy recommendations add value over both passive benchmarks and random selection, and what does the internal agent structure reveal about the source of the edge?
  arXiv  Detail & Related papers  (2026-04-19T08:43:31Z)
• Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees [13.891522069967507]
  Large Language Model (LLM) agents are increasingly deployed in multi-agent systems requiring strategic coordination.<n>We present the first framework grounding coalition formation in LLM agent networks in hedonic game theory with formal stability guarantees.
  arXiv  Detail & Related papers  (2026-04-15T19:59:30Z)
• Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System [29.738672424331398]
  We introduce the Shapley-based Hierarchical Attribution for Reinforcement Policy (SHARP), a novel framework for optimizing multi-agent reinforcement learning via precise credit attribution.<n>SHARP stabilizes training by normalizing agent-specific advantages across trajectory groups, primarily through a global broadcast-accuracy reward, and a tool-process reward to improve execution efficiency.<n>Experiments demonstrate that SHARP significantly outperforms recent state-of-the-art baselines, achieving average match improvements of 23.66% and 14.05% over single-agent and multi-agent approaches, respectively.
  arXiv  Detail & Related papers  (2026-02-09T07:17:28Z)
• SAMP-HDRL: Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management via Hierarchical Deep Reinforcement Learning [4.743963988265057]
  We propose a Segmented Allocation with Momentum-Adjusted Utility for Multi-agent Portfolio Management.<n>The framework integrates dynamic asset grouping to partition the market into high-quality and ordinary subsets.<n>Our method achieves at least 5% higher Return, 5% higher Sortino ratio, and 2% higher Omega ratio, with substantially larger gains.
  arXiv  Detail & Related papers  (2025-12-28T11:56:39Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model [56.92219181993453]
  We propose Reincarnating Mix-policy Proximal Policy Gradient (ReMix) to enable on-policyRFT methods like PPO and GRPO to leverage off-policy data.<n>ReMix consists of three major components: (1) Mix-policy proximal policy gradient with an increased Update-To-Data (UTD) ratio for efficient training; (2) KL-Convex policy constraint to balance the trade-off between stability and flexibility; (3) Policy reincarnation to achieve a seamless transition from efficient early-stage learning to steady improvement.
  arXiv  Detail & Related papers  (2025-07-09T14:29:45Z)
• Decentralised Q-Learning for Multi-Agent Markov Decision Processes with a Satisfiability Criterion [0.0]
  We propose a reinforcement learning algorithm to solve a multi-agent Markov decision process (MMDP) The goal is to lower the time average cost of each agent to below a pre-specified agent-specific bound.
  arXiv  Detail & Related papers  (2023-11-21T13:56:44Z)
• AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation [65.4532392602682]
  One of the main challenges in offline Reinforcement Learning (RL) is the distribution shift that arises from the learned policy deviating from the data collection policy. This is often addressed by avoiding out-of-distribution (OOD) actions during policy improvement as their presence can lead to substantial performance degradation. We introduce AlberDICE, an offline MARL algorithm that performs centralized training of individual agents based on stationary distribution optimization.
  arXiv  Detail & Related papers  (2023-11-03T18:56:48Z)
• Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO [66.5384483339413]
  We present a new monotonic improvement guarantee for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL) We show that a trust region constraint can be effectively enforced in a principled way by bounding independent ratios based on the number of agents in training.
  arXiv  Detail & Related papers  (2022-01-31T20:39:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.