# Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making

arXiv: https://arxiv.org/abs/2511.12876 · HTML: https://mlsanity.com/paper/2511.12876/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 8 of 8)

- [TradingAgents: Multi-Agents LLM Financial Trading Framework](https://mlsanity.com/paper/2412.20138/) (2024)
- [A Survey of Reinforcement Learning Informed by Natural Language](https://mlsanity.com/paper/1906.03926/) (2019)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Emergent Bartering Behaviour in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2205.06760/) (2022)
- [Deep Reinforcement Learning in a Monetary Model](https://mlsanity.com/paper/2104.09368/) (2021)
- [A Multi-LLM-Agent-Based Framework for Economic and Public Policy Analysis](https://mlsanity.com/paper/2502.16879/) (2025)
- [An Economy of Neural Networks: Learning from Heterogeneous Experiences](https://mlsanity.com/paper/2110.11582/) (2021)
- [Can an AI agent hit a moving target?](https://mlsanity.com/paper/2110.02474/) (2021)

## Built on by (most cited first, 2 of 2)

- [From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models](https://mlsanity.com/paper/2608.06020/) (2026)
- [A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing](https://mlsanity.com/paper/2608.07148/) (2026)

## Abstract (arXiv)

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.