mlsanityData to 14 Oct 2026

AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making

arXiv 2411.03865 ↗First posted 6 Nov 2024cs.MA cs.AI cs.GTcited by 20

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Traditional interactive environments limit agents' intelligence growth with fixed tasks. Recently, single-agent environments address this by generating new tasks based on agent actions, enhancing task diversity. We consider the decision-making problem in multi-agent settings, where tasks are further influenced by social connections, affecting rewards and information access. However, existing multi-agent environments lack a combination of adaptive physical surroundings and social connections, hindering the learning of intelligent behaviors. To address this, we introduce AdaSociety, a customizable multi-agent environment featuring expanding state and action spaces, alongside explicit and alterable social structures. As agents progress, the environment adaptively generates new tasks with social structures for agents to undertake. In AdaSociety, we develop three mini-games showcasing distinct social structures and tasks. Initial results demonstrate that specific social structures can promote both individual and collective benefits, though current reinforcement learning and LLM-based algorithms show limited effectiveness in leveraging social structures to enhance performance. Overall, AdaSociety serves as a valuable research platform for exploring intelligence in diverse physical and social settings. The code is available at https://github.com/bigai-ai/AdaSociety.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 38 of its 89 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

38 of 89 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents27 Jun
  2. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models10 Nov
  3. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory25 May
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May
  5. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge17 Jun

Other references · 33

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  5. 2019The StarCraft Multi-Agent Challengecited by 597
  6. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  7. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  8. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  9. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  10. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  11. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
  12. 2018Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agentscited by 194
21 more
  1. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 186
  2. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 182
  3. 2019A Review of Cooperative Multi-Agent Deep Reinforcement Learningcited by 147
  4. 2017Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problemscited by 131
  5. 2019Deep Coordination Graphscited by 98
  6. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 71
  7. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 60
  8. 2020Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Rewardcited by 50
  9. 2022Melting Pot 2.0cited by 40
  10. 2022No-Regret Learning in Time-Varying Zero-Sum Gamescited by 36
  11. 2022Sample-Efficient Reinforcement Learning of Partially Observable Markov Gamescited by 27
  12. 2020Learning Structured Communication for Multi-agent Reinforcement Learningcited by 21
  13. 2023Stabilizing Unsupervised Environment Design with a Learned Adversarycited by 17
  14. 2022Grounding Aleatoric Uncertainty for Unsupervised Environment Designcited by 16
  15. 2023On the Convergence of No-Regret Learning Dynamics in Time-Varying Gamescited by 14
  16. 2020Learning Multi-Agent Coordination through Connectivity-driven Communicationcited by 10
  17. 2023Active Reasoning in an Open-World Environmentcited by 8
  18. 2024Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planningcited by 7
  19. 2020Fully Asynchronous Policy Evaluation in Distributed Reinforcement Learning over Networkscited by 6
  20. 2024Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Gamescited by 6
  21. 2019Competing Against Equilibria in Zero-Sum Games with Evolving Payoffscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 14; 2026: 4.

20 papers.

Sort:

By area:

  1. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  2. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 55
  3. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 23
  4. 2025SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoningcited by 18
  5. 2025GNNs as Predictors of Agentic Workflow Performancescited by 17
  6. 2024Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspectivecited by 9
  7. 2025Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systemscited by 5
  8. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 5
  9. 2025Games Agents Play: Towards Transactional Analysis in LLM-based Multi-Agent Systemscited by 3
  10. 2025Social World Model-Augmented Mechanism Design Policy Learningcited by 3
  11. 2025Orchestrator: Active Inference for Multi-Agent Systems in Long-Horizon Taskscited by 2
  12. 2025SimCity: Multi-Agent Urban Development Simulation with Rich Interactionscited by 2
8 more
  1. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  2. 2025TACLA: An LLM-Based Multi-Agent Tool for Transactional Analysis Training in Educationcited by 1
  3. 2025IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environmentcited by 0
  4. 2025On the Role of Contextual Information and Ego States in LLM Agent Behavior for Transactional Analysis Dialoguescited by 0
  5. 2026Adaptive Punishment for Cooperation in Mixed-Motive Gamescited by 0
  6. 2026SidConArena: An Environment Evaluating Agents in Open-Ended,Positive-Sum Bargaining Gamecited by 0
  7. 2026From Optimal Policies to Individual Differences: Rethinking Reinforcement Learning for Biologycited by 0
  8. 2026Grounded Normative Rule Generation with Structured Searchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings
  2. 2026Communicate-Predict-Act: Evaluating Social Intelligence of Agents
  3. 2020Emergent Social Learning via Multi-agent Reinforcement Learning
  4. 2026Multi-Agent LLMs Fail to Explore Each Other
  5. 2024The impact of behavioral diversity in multi-agent reinforcement learning
  6. 2026Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments
  7. 2025Sorrel: A simple and flexible framework for multi-agent reinforcement learning
  8. 2026When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail