# Social World Model-Augmented Mechanism Design Policy Learning

arXiv: https://arxiv.org/abs/2510.19270 · HTML: https://mlsanity.com/paper/2510.19270/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 27 of its 38 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning](https://mlsanity.com/paper/1910.08348/) (2019)
- [Learning Latent Representations to Influence Multi-Agent Interaction](https://mlsanity.com/paper/2011.06619/) (2020)
- [The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies](https://mlsanity.com/paper/2004.13332/) (2020)
- [A multi-agent reinforcement learning model of common-pool resource appropriation](https://mlsanity.com/paper/1707.06600/) (2017)
- [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024)
- [CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents](https://mlsanity.com/paper/2401.10568/) (2024)
- [M3RL: Mind-aware Multi-agent Management Reinforcement Learning](https://mlsanity.com/paper/1810.00147/) (2018)
- [AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making](https://mlsanity.com/paper/2411.03865/) (2024)
- [Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects](https://mlsanity.com/paper/2203.10603/) (2022)
- [Reinforcement Mechanism Design, with Applications to Dynamic Pricing in Sponsored Search Auctions](https://mlsanity.com/paper/1711.10279/) (2017)
- [Inference Aided Reinforcement Learning for Incentive Mechanism Design in Crowdsourcing](https://mlsanity.com/paper/1806.00206/) (2018)
- [Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning](https://mlsanity.com/paper/2406.08002/) (2024)
- [Enhancing LLM-Based Social Bot via an Adversarial Learning Framework](https://mlsanity.com/paper/2508.17711/) (2025)
- [LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2405.19998/) (2024)
- [Pessimism meets VCG: Learning Dynamic Mechanism Design via Offline Reinforcement Learning](https://mlsanity.com/paper/2205.02450/) (2022)
- [MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.06011/) (2023)
- [Differentiable Information Enhanced Model-Based Reinforcement Learning](https://mlsanity.com/paper/2503.01178/) (2025)

## Built on by (most cited first, 3 of 3)

- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [Building Social World Models with Large Language Models](https://mlsanity.com/paper/2606.11482/) (2026)
- [Grounded Normative Rule Generation with Structured Search](https://mlsanity.com/paper/2608.22229/) (2026)

## Abstract (arXiv)

Designing adaptive mechanisms to align individual and collective interests remains a central challenge in artificial social intelligence. Existing methods often struggle with modeling heterogeneous agents possessing persistent latent traits (e.g., skills, preferences) and dealing with complex multi-agent system dynamics. These challenges are compounded by the critical need for high sample efficiency due to costly real-world interactions. World Models, by learning to predict environmental dynamics, offer a promising pathway to enhance mechanism design in heterogeneous and complex systems. In this paper, we introduce a novel method named SWM-AP (Social World Model-Augmented Mechanism Design Policy Learning), which learns a social world model hierarchically modeling agents' behavior to enhance mechanism design. Specifically, the social world model infers agents' traits from their interaction trajectories and learns a trait-based model to predict agents' responses to the deployed mechanisms. The mechanism design policy collects extensive training trajectories by interacting with the social world model, while concurrently inferring agents' traits online during real-world interactions to further boost policy learning efficiency. Experiments in diverse settings (tax policy design, team coordination, and facility location) demonstrate that SWM-AP outperforms established model-based and model-free RL baselines in cumulative rewards and sample efficiency.