mlsanityData to 14 Oct 2026

Cooperative AI via Decentralized Commitment Devices

arXiv 2311.07815 ↗First posted 14 Nov 2023cs.AI cs.CR cs.GTcited by 7

Not on the map. Why?

Abstract (arXiv)

Credible commitment devices have been a popular approach for robust multi-agent coordination. However, existing commitment mechanisms face limitations like privacy, integrity, and susceptibility to mediator or user strategic behavior. It is unclear if the cooperative AI techniques we study are robust to real-world incentives and attack vectors. However, decentralized commitment devices that utilize cryptography have been deployed in the wild, and numerous studies have shown their ability to coordinate algorithmic agents facing adversarial opponents with significant economic incentives, currently in the order of several million to billions of dollars. In this paper, we use examples in the decentralization and, in particular, Maximal Extractable Value (MEV) (arXiv:1904.05234) literature to illustrate the potential security issues in cooperative AI. We call for expanded research into decentralized commitments to advance cooperative AI capabilities for secure coordination in open environments and empirical testing frameworks to evaluate multi-agent coordination ability given real-world commitment constraints.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 46 of its 89 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

46 of 89 references.

References · 46

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  2. 2016Concrete Problems in AI Safetycited by 1,642
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  4. 2018Behavioral Cloning from Observationcited by 492
  5. 2017Learning with Opponent-Learning Awarenesscited by 222
  6. 2020"Other-Play" for Zero-Shot Coordinationcited by 198
  7. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
  8. 2020Open Problems in Cooperative AIcited by 168
  9. 2023Regulating ChatGPT and other Large Generative AI Modelscited by 104
  10. 2020Learning Latent Representations to Influence Multi-Agent Interactioncited by 93
  11. 2021Off-Belief Learningcited by 75
  12. 2022Model-Free Opponent Shapingcited by 44
34 more
  1. 2022COLA: Consistent Learning with Opponent-Learning Awarenesscited by 38
  2. 2021A New Formalism, Method and Open Issues for Zero-Shot Coordinationcited by 33
  3. 2022Scaling up Trustless DNN Inference with Zero-Knowledge Proofscited by 31
  4. 2020The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learningcited by 28
  5. 2021SoK: Decentralized Finance (DeFi)cited by 23
  6. 2021Auctions Between Regret-Minimizing Agentscited by 22
  7. 2022Artificial Intelligence and Auction Designcited by 20
  8. 2022Influencing Long-Term Behavior in Multiagent Reinforcement Learningcited by 18
  9. 2021How and Why to Manipulate Your Own Agent: On the Incentives of Users of Learning Agentscited by 17
  10. 2020A Survey on Blockchain Interoperability: Past, Present, and Future Trendscited by 13
  11. 2023Game Theory with Simulation of Other Playerscited by 13
  12. 2019An analysis of Uniswap marketscited by 12
  13. 2022Cooperative and uncooperative institution designs: Surprises and problems in open-source game theorycited by 11
  14. 2022Meta-Learning in Gamescited by 10
  15. 2020Learning to Resolve Alliance Dilemmas in Many-Player Zero-Sum Gamescited by 9
  16. 2020Attacking the DeFi Ecosystem with Flash Loans for Fun and Profitcited by 9
  17. 2022Game-Theoretical Perspectives on Active Equilibria: A Preferred Solution Concept over Nash Equilibriacited by 5
  18. 2023Mediated Multi-Agent Reinforcement Learningcited by 5
  19. 2014Decentralized Anti-coordination Through Multi-agent Learningcited by 4
  20. 2022Commitment games with conditional information disclosurecited by 4
  21. 2022Formal Contracts Mitigate Social Dilemmas in Multi-Agent RLcited by 4
  22. 2021Improving Social Welfare While Preserving Autonomy via a Pareto Mediatorcited by 3
  23. 2022Optimal Routing for Constant Function Market Makerscited by 3
  24. 2023UN Handbook on Privacy-Preserving Computation Techniquescited by 3
  25. 2023Auctions without commitment in the auto-bidding worldcited by 3
  26. 2020Credible, Truthful, and Two-Round (Optimal) Auctions via Cryptographic Commitmentscited by 2
  27. 2022Towards a Theory of Maximal Extractable Value I: Constant Function Market Makerscited by 2
  28. 2022What Can Cryptography Do For Decentralized Mechanism Designcited by 2
  29. 2022Credible Decentralized Exchange Design via Verifiable Sequencing Rulescited by 2
  30. 2023Transaction Fee Mechanism Design with Active Block Producerscited by 2
  31. 2023Side Contract Commitment Attacks on Blockchainscited by 1
  32. 2023Credible, Optimal Auctions via Public Broadcastcited by 1
  33. 2023The Cost of Sybils, Credible Commitments, and False-Name Proof Mechanismscited by 1
  34. 2023Stackelberg Attacks on Auctions and Blockchain Transaction Fee Mechanismscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 1.

7 papers.

  1. 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganographycited by 113
  2. 2025Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agentscited by 71
  3. 2025Infrastructure for AI Agentscited by 41
  4. 2024IDs for AI Systemscited by 19
  5. 2024Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contractscited by 9
  6. 2026Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physicscited by 2
  7. 2025Policy-Conditioned Policies for Multi-Agent Task Solvingcited by 0