English

Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning

Machine Learning 2026-07-05 v1 Artificial Intelligence Optimization and Control

Abstract

Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood. We show that dynamically updating LLM-generated reward weights during off-policy MARL violates the stationarity assumption of Potential-Based Reward Shaping (PBRS) and contaminates the experience replay buffer, whose stored transitions carry reward labels computed under stale shaping weights. We characterise the result as a regime-dependent failure whose severity depends on how competent the unshaped baseline already is. To control it we propose two stabilisation strategies: a Phase-Based Freeze Schedule that enforces strict stationarity within training phases, and Exponential Moving Average (EMA) smoothing that bounds per-episode weight drift. We evaluate across three cooperative environments and five random seeds with QMIX, complemented by an exploratory VDN extension, yielding a three-regime taxonomy. In the augmentative regime (Simple Spread), where the baseline is functional (74.4 %), EMA significantly improves success to 86.7 % (+12.3+12.3 pp, p<0.01p<0.01) while naive dynamic updates collapse it to 15.2 %. In the essential regime (Level-Based Foraging), where the baseline is broken (0.1 %), any shaping unlocks the task (95.9 % under EMA). In the supplementary regime (SMAC 3m), where the baseline is near-saturated (98.8 %), stabilised shaping preserves performance (99.9 %) while unstabilised shaping adds variance without gain. These findings establish reward-signal stationarity as a necessary design constraint and indicate that regime placement is a practical predictor of whether dynamic LLM shaping helps or harms.

Cite

@article{arxiv.2607.04470,
  title  = {Regime-Conditional Stabilisation of LLM-Augmented Cooperative Multi-Agent Reinforcement Learning},
  author = {Faid Keddouri and Sohaib Houhou and Aissa Boulmerka and Nadir Farhi},
  journal= {arXiv preprint arXiv:2607.04470},
  year   = {2026}
}
R2 v1 2026-07-22T20:23:28.280Z