mlsanityData to 7 Oct 2026

Deep Incentive Design with Differentiable Equilibrium Blocks

arXiv 2603.07705 ↗First posted 8 Mar 2026cs.GT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Automated design of multi-agent interactions with desirable equilibrium outcomes is inherently difficult due to the computational hardness, non-uniqueness, and instability of the resulting equilibria. In this work, we propose the use of game-agnostic differentiable equilibrium blocks (DEBs) as modules in a novel, differentiable framework to address a wide variety of incentive design problems from economics and computer science. We call this framework deep incentive design (DID). To validate our approach, we examine three diverse, challenging incentive design tasks: contract design, machine scheduling, and inverse equilibrium problems. For each task, we train a single neural network using a unified pipeline and DEB. This architecture solves the full distribution of problem instances, parameterized by a context, handling all games across a wide range of scales (from two to sixteen actions per player).

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 46 of its 84 references that are in the map. First posted on arXiv 8 Mar 2026.

Builds on

46 of 84 references.

References · 46

  1. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  2. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  3. 2024RouterBench: A Benchmark for Multi-LLM Routing Systemcited by 222
  4. 2023Nash Learning from Human Feedbackcited by 220
  5. 2017Sobolev Training for Neural Networkscited by 136
  6. 2021V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RLcited by 111
  7. 2020Near-Optimal Reinforcement Learning with Self-Playcited by 108
  8. 2025Universal Model Routing for Efficient LLM Inferencecited by 80
  9. 2020Aligning Superhuman AI with Human Behavior: Chess as a Model Systemcited by 78
  10. 2021Modeling Strong and Human-Like Gameplay with KL-Regularized Searchcited by 50
  11. 2022Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planningcited by 47
  12. 2024Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHFcited by 41
34 more
  1. 2017Optimal Auctions through Deep Learning: Advances in Differentiable Economicscited by 38
  2. 2023PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedbackcited by 38
  3. 2014Complexity of Mechanism Designcited by 33
  4. 2020Auction learning as a two-player gamecited by 29
  5. 2022Optimal-er Auctions through Attentioncited by 26
  6. 2013Computational Rationalization: The Inverse Equilibrium Problemcited by 24
  7. 2023A Scalable Neural Network for DSIC Affine Maximizer Auction Designcited by 23
  8. 2018What game are we playing? End-to-end learning in normal and extensive form gamescited by 22
  9. 2020End-to-End Learning and Intervention in Gamescited by 19
  10. 2022A Context-Integrated Transformer-Based Neural Network for Auction Designcited by 19
  11. 2022Multi-Agent Contractscited by 14
  12. 2024Contextual Bilevel Reinforcement Learning for Incentive Alignmentcited by 14
  13. 2021Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Gamescited by 10
  14. 2022The Good Shepherd: An Oracle Agent for Mechanism Designcited by 10
  15. 2022Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Neural Equilibrium Solverscited by 10
  16. 2018Adaptive Mechanism Design: Learning to Promote Cooperationcited by 9
  17. 2018Disciplined Geometric Programmingcited by 8
  18. 2021Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergencecited by 8
  19. 2024Automated Design of Affine Maximizer Mechanisms in Dynamic Settingscited by 7
  20. 2023Multi-Agent Contract Design: How to Commission Multiple Agents with Individual Outcomecited by 6
  21. 2023BIG Hype: Best Intervention in Games via Distributed Hypergradient Descentcited by 5
  22. 2025Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providerscited by 5
  23. 2022Inducing Social Optimality in Games via Adaptive Incentive Designcited by 4
  24. 2022Differentiable Bilevel Programming for Stackelberg Congestion Gamescited by 4
  25. 2019Learning Truthful, Efficient, and Welfare Maximizing Auction Rulescited by 3
  26. 2024Multi-Agent Contract Design beyond Binary Actionscited by 3
  27. 2017Inference on Auctions with Weak Assumptions on Informationcited by 2
  28. 2023Achieving Hierarchy-Free Approximation for Bilevel Programs With Equilibrium Constraintscited by 2
  29. 2023Equilibrium-Invariant Embedding, Metric Space, and Fundamental Set of 2×2 Normal-Form Gamescited by 2
  30. 2024Learning to Steer Markovian Agents under Model Uncertaintycited by 2
  31. 2024NfgTransformer: Equivariant Representation Learning for Normal-form Gamescited by 1
  32. 2024Learning and steering game dynamics towards desirable outcomescited by 1
  33. 2025Scalable Neural Incentive Design with Parameterized Mean-Field Approximationcited by 1
  34. 2025Black-Box Lifting and Robustness Theorems for Multi-Agent Contractscited by 1

Built on by

Not cited yet.