mlsanityData to 7 Oct 2026

Microeconomic Foundations of Multi-Agent Learning

arXiv 2601.03451 ↗First posted 6 Jan 2026stat.ML cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern AI systems increasingly operate inside markets and institutions where data, behavior, and incentives are endogenous. This paper develops an economic foundation for multi-agent learning by studying a principal-agent interaction in a Markov decision process with strategic externalities, where both the principal and the agent learn over time. We propose a two-phase incentive mechanism that first estimates implementable transfers and then uses them to steer long-run dynamics; under mild regret-based rationality and exploration conditions, the mechanism achieves sublinear social-welfare regret and thus asymptotically optimal welfare. Simulations illustrate how even coarse incentives can correct inefficient learning under stateful externalities, highlighting the necessity of incentive-aware design for safe and welfare-aligned AI in markets and insurance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

27 of 53 references.

References · 27

  1. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  2. 2020Performative Predictioncited by 318
  3. 2024Reinforcement learningcited by 236
  4. 2024Secrets of RLHF in Large Language Models Part II: Reward Modelingcited by 170
  5. 2020Stochastic Optimization for Performative Predictioncited by 92
  6. 2024Reinforcement Learning for LLM Post-Training: A Surveycited by 91
  7. 2020Performative Prediction in a Stateful Worldcited by 90
  8. 2025Reward Shaping to Mitigate Reward Hacking in RLHFcited by 88
  9. 2024Sharp Analysis for KL-Regularized Contextual Bandits and RLHFcited by 32
  10. 2024Optimal Design for Reward Modeling in RLHFcited by 23
  11. 2022Multi-Agent Contractscited by 14
  12. 2024Incentivized Learning in Principal-Agent Bandit Gamescited by 13
15 more
  1. 2021Combinatorial Contractscited by 12
  2. 2021Exploration and Incentives in Reinforcement Learningcited by 11
  3. 2023Delegated Classificationcited by 10
  4. 2025The Agentic Economycited by 9
  5. 2023Delegating Data Collection in Decentralized Machine Learningcited by 8
  6. 2024Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contractscited by 8
  7. 2024Unravelling in Collaborative Learningcited by 6
  8. 2024Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationalitycited by 3
  9. 2025The Pseudo-Dimension of Contractscited by 3
  10. 2024Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agentscited by 2
  11. 2025Online Decision-Making in Tree-Like Multi-Agent Games with Transferscited by 2
  12. 2025Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivalscited by 2
  13. 2025Steering No-Regret Agents in MFGs under Model Uncertaintycited by 1
  14. 2025Learning to Lead: Incentivizing Strategic Agents in the Darkcited by 1
  15. 2025Fair Contracts in Principal-Agent Games with Heterogeneous Typescited by 1

Built on by

Not cited yet.