Research map / Multi-agent systems and games / Cooperative multi-agent RL
Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
Heyang Ma, Qirui Mi, Qipeng Yang, Zijun Fan, Bo Li, Haifeng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LLM reasoning and language (LAMP) to MARL | MADDPG · TaxAI S1 Economic Stability | Avg. household reward: 5.21 -> 8.52 | Improved |
| add LLM reasoning and language (LAMP) over Rule-Based baseline | Rule-Based · TaxAI S1 Economic Stability | Social welfare: 2.28e+03 -> 2.56e+03 | Improved |
| couple LLM reasoning with MARL policy instead of LLM-only prompting (vs ReAct) | LLM baselines · TaxAI S1 Economic Stability | Social welfare: 2.23e+03 -> 2.56e+03 | Improved |
| add Speak module (strategic messaging and belief updates) (ablation) | LAMP · TaxAI S1 Economic Stability | Social welfare: 2.53e+03 -> 2.56e+03; labor 5.36e+05 -> 3.13e+05 | Improved |
| add experience pool of high-reward reasoning trajectories (ablation) | LAMP · TaxAI S1 Economic Stability | Social welfare: 1.25e+03 -> 2.56e+03 | Improved |
| add experience pool of high-reward reasoning trajectories (ablation) | LAMP · TaxAI S1 Economic Stability | Avg. household reward: 8.45 -> 8.52 | No clear effect |
| add long-term reasoning (ablation) | LAMP · TaxAI S1 Economic Stability | Avg. household reward: 5.31 -> 8.52 | Improved |
| add short-term reasoning (ablation) | LAMP · TaxAI S1 Economic Stability | Stable years: 208 -> 300 | Improved |
| use shock-triggered timing scheduler instead of random triggers (ablation) | LAMP · TaxAI S1 Economic Stability | Stable years: 141 -> 300 | Improved |
| use shock-triggered timing scheduler instead of random triggers (ablation) | LAMP · TaxAI S1 Economic Stability | Avg. household reward: 8.52 -> 8.52 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Reflexion — Reflexion: language agents with verbal reinforcement learning (NeurIPS 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models (NeurIPS 2025 · similarity 0.87)
- FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (NeurIPS 2024 · similarity 0.86)
- STEER: Assessing the Economic Rationality of Large Language Models (ICML 2024 · similarity 0.86)
- EconGym: A Scalable AI Testbed with Diverse Economic Tasks (NeurIPS 2025 · similarity 0.85)
- Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making (ICML 2025 · similarity 0.85)
- From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
