AI Paper Atlas

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

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
add LLM reasoning and language (LAMP) to MARLMADDPG · TaxAI S1 Economic StabilityAvg. household reward: 5.21 -> 8.52Improved
add LLM reasoning and language (LAMP) over Rule-Based baselineRule-Based · TaxAI S1 Economic StabilitySocial welfare: 2.28e+03 -> 2.56e+03Improved
couple LLM reasoning with MARL policy instead of LLM-only prompting (vs ReAct)LLM baselines · TaxAI S1 Economic StabilitySocial welfare: 2.23e+03 -> 2.56e+03Improved
add Speak module (strategic messaging and belief updates) (ablation)LAMP · TaxAI S1 Economic StabilitySocial welfare: 2.53e+03 -> 2.56e+03; labor 5.36e+05 -> 3.13e+05Improved
add experience pool of high-reward reasoning trajectories (ablation)LAMP · TaxAI S1 Economic StabilitySocial welfare: 1.25e+03 -> 2.56e+03Improved
add experience pool of high-reward reasoning trajectories (ablation)LAMP · TaxAI S1 Economic StabilityAvg. household reward: 8.45 -> 8.52No clear effect
add long-term reasoning (ablation)LAMP · TaxAI S1 Economic StabilityAvg. household reward: 5.31 -> 8.52Improved
add short-term reasoning (ablation)LAMP · TaxAI S1 Economic StabilityStable years: 208 -> 300Improved
use shock-triggered timing scheduler instead of random triggers (ablation)LAMP · TaxAI S1 Economic StabilityStable years: 141 -> 300Improved
use shock-triggered timing scheduler instead of random triggers (ablation)LAMP · TaxAI S1 Economic StabilityAvg. household reward: 8.52 -> 8.52No 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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy