mlsanityData to 14 Oct 2026

MEMOA: Massive Mixtures of Online Agents via Mean-Field Decentralized Nash Equilibria

arXiv 2605.05492 ↗First posted 6 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In the modern age of large-scale AI, federated learning has become an increasingly important tool for training large populations of AI agents; however, its computational and communication costs can rapidly fail to scale with the number of agents. This is precisely where decentralized agentic strategies shine: each agent acts autonomously, using only its own state together with a minimal summary of the ensemble, namely the mean-field. We derive the unique optimal decentralized policy in closed form. Optimality is characterized through a worst-client/minimax criterion: minimizing the under-performer regret, namely the maximal online cost incurred by the weakest agent in the ensemble. We further prove that the resulting decentralized policy asymptotically converges, in the large-population limit, to the Nash-optimal centralized policy, whose direct computation is not scalable. We use an online weighting mechanism to optimize the server-computed mixture of client predictions, thereby improving the mean prediction in addition to the previously optimized weakest-client prediction. Numerical experiments verify our theoretical guarantees and demonstrate that our decentralized policy typically outperforms natural greedy decentralized baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 47 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

23 of 47 references.

References · 23

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
  6. 2022Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Modelcited by 265
  7. 2023Power Hungry Processing: Watts Driving the Cost of AI Deployment?cited by 191
  8. 2023From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inferencecited by 170
  9. 2018Echo state networks are universalcited by 87
  10. 2023LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Modelscited by 72
  11. 2020Model-sharing Games: Analyzing Federated Learning Under Voluntary Participationcited by 60
  12. 2025Reducing Cost of LLM Agents with Trajectory Reductioncited by 48
11 more
  1. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 44
  2. 2021Optimality and Stability in Federated Learning: A Game-theoretic Approachcited by 40
  3. 2022On Privacy and Personalization in Cross-Silo Federated Learningcited by 36
  4. 2026How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Taskscited by 33
  5. 2020Communication-Efficient Massive UAV Online Path Control: Federated Learning Meets Mean-Field Game Theorycited by 16
  6. 2021Federated Learning as a Mean-Field Gamecited by 4
  7. 2019Linear quadratic mean field games: Asymptotic solvability and relation to the fixed point approachcited by 3
  8. 2023Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Datacited by 3
  9. 2021Linear quadratic mean field games: Decentralized O(1/N)-Nash equilibriacited by 1
  10. 2025Online Federation For Mixtures of Proprietary Agents with Black-Box Encoderscited by 1
  11. 2026Privacy as Commodity: MFG-RegretNet for Large-Scale Privacy Trading in Federated Learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Convergence of Decentralized Actor-Critic Algorithm in General-sum Markov Games
  2. 2026High-Probability Nash Regret for Decentralized Learning in Markov α-Potential Games: Episodic and Fully Online Asynchronous Algorithms with Applications to Markov Congestion Games
  3. 2025On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments
  4. 2026Agentic Federated Learning: The Future of Distributed Training Orchestration
  5. 2026Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost
  6. 2024Towards Fast Rates for Federated and Multi-Task Reinforcement Learning
  7. 2024MF-OML: Online Mean-Field Reinforcement Learning with Occupation Measures for Large Population Games
  8. 2025Vairiational Stochastic Games