{"ID":2840294,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.12876","arxiv_id":"2511.12876","title":"Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making","abstract":"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.","short_abstract":"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 cont...","url_abs":"https://arxiv.org/abs/2511.12876","url_pdf":"https://arxiv.org/pdf/2511.12876v4","authors":"[\"Heyang Ma\",\"Qirui Mi\",\"Qipeng Yang\",\"Zijun Fan\",\"Bo Li\",\"Haifeng Zhang\"]","published":"2025-11-17T02:09:18Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"econ.GN\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}