Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
By: Heyang Ma , Qirui Mi , Qipeng Yang and more
Potential Business Impact:
Helps computers make smarter money choices with words.
Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While multi-agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language-Augmented Multi-Agent Policy), a framework that integrates language into economic decision-making and narrows the gap to real-world settings. LAMP follows a Think-Speak-Decide pipeline: (1) Think interprets numerical observations to extract short-term shocks and long-term trends, caching high-value reasoning trajectories; (2) Speak crafts and exchanges strategic messages based on reasoning, updating beliefs by parsing peer communications; and (3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language-augmented decision-making. Experiments in economic simulation show that LAMP outperforms both MARL and LLM-only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrate the potential of language-augmented policies to deliver more effective and robust economic strategies.
Similar Papers
Language-Guided Multi-Agent Learning in Simulations: A Unified Framework and Evaluation
Artificial Intelligence
Helps AI teams work together better in games.
LAMARL: LLM-Aided Multi-Agent Reinforcement Learning for Cooperative Policy Generation
Robotics
Robots learn tasks faster with AI help.
Towards Language-Augmented Multi-Agent Deep Reinforcement Learning
Multiagent Systems
Teaches robots to talk and work together.