Principal-Agent Theory

Follow this topic Ask about this topic

Latest papers

13 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Contracting with an Agent under Model Mismatch
Oct 16, 2026Elif Yılmaz, Jakub Tłuczek, Victor Villin +1Principal-Agent Theory Model Misspecification
University of Neuchâtel Neuchâtel, Switzerland
Anytime Contracts for AI Services
Oct 16, 2026Boris Velasevic, Eden Saig, Eric MazumdarPrincipal-Agent Theory
California Institute of Technology
Multi-Agent AI as a Nested Principal-Agent Problem in Private Wealth Management: Mandate Representation and Evidence Control in Switzerland, Germany and Austria
Oct 2, 2026Walter Kurz, Reinhard Magg, Florian Kollberg +4Financial Services AI Agent Governance
Swissi Institute for AI · Hochschule für Wirtschaft und Umwelt Nürtingen-Geislingen · Faculty of Information Technology and Engineering (FITI), Belgrade
Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts
Sep 17, 2026Rui Ai, David Simchi-Levi, Han ZhongMechanism Design Minimax Regret
Massachusetts Institute of Technology · Shanghai Jiao Tong University
Mechanism Design for Alignment and Control
Sep 1, 2026Dirk Bergemann, Andrew Koh, Stephen MorrisMechanism Design Principal-Agent Theory
Yale · Columbia · MIT +1
Contracting for LLM Delegation: Moral Hazard in Technology and Effort Choice
Aug 18, 2026Nanda Kishore Sreenivas, Kate LarsonPrincipal-Agent Theory LLM Agents
University of Waterloo
Adaptive Incentive Design in Dynamic Principal-Agent Problem via Kernelized Bandits
Aug 18, 2026Arghya Mallick, Anuj S. Vora, Sergio Grammatico +1Principal-Agent Theory Mechanism Design
Delft Center for Systems and Control, Delft University of Technology, Delft, The Netherlands · Jio Institute, Navi Mumbai, India · University of Toronto, Toronto, Canada
Optimal Liability Design for Medical AI
Aug 4, 2026Rui Mao, Tingliang Huang, Houcai ShenMechanism Design AI Accountability
School of Management & Engineering, Nanjing University, Nanjing 210093, China · Haslam College of Business, University of Tennessee, Knoxville, TN 37996, USA
How to Detect and Measure the AI Dangers to Democracy
Jun 14, 2026Giulia Sandri, Claudio NovelliAI Accountability Principal-Agent Theory
Université libre de Bruxelles · DEC, Yale University
Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
May 29, 2026Andreas Haupt, Justin Hartenstein, Anka Reuel +2Principal-Agent Theory Algorithmic Auditing
Institute for Computational and Mathematical Engineering Stanford University · Department of Computer Science Stanford University
AI Alignment via Incentives and Correction
May 2, 2026Rohit Agarwal, Joshua Lin, Mark Braverman +1Principal-Agent Theory AI Alignment
Princeton University
Optimally Auditing Adversarial Agents
Apr 28, 2026Sanmay Das, Fang-Yi Yu, Yuang ZhangAlgorithmic Auditing Game Theory
Virginia Tech · George Mason University
Power and Limitations of Aggregation in Compound AI Systems
Feb 25, 2026Nivasini Ananthakrishnan, Meena JagadeesanMulti-Agent LLM Systems Principal-Agent Theory
UC Berkeley · Stanford University

Oct 16, 2026J/K move · Enter open · S save

Contracting with an Agent under Model Mismatch

Elif Yılmaz, Jakub Tłuczek, Victor Villin, Christos Dimitrakakis

University of Neuchâtel Neuchâtel, Switzerland

Principal-Agent Theory Model Misspecification Mechanism Design Markov Decision Processes

Open paper AskPDF arXiv

In the classical principal-agent setting, the principal delegates some task to the agent, who receives a payment conditioned on the outcome of the task, which in turn benefits the principal. To align their objectives, the principal designs a contract that incentivizes the agent to take actions beneficial to the principal. In practice, however, the agent may act under misspecified beliefs about the underlying environment, leading to systematically suboptimal decisions. In this work, we study this problem through a principal-agent Markov Decision Process (PAMDP), in which the principal repeatedly interacts with an agent whose transition model may differ from the true environment dynamics. The principal has access to the true transition model and designs contracts that account for the agent's belief and incentives. We characterize contract design under model mismatch and develop a framework that enables the principal to induce desirable long-term benefits even though the agent has a potentially inaccurate understanding of the environment.