Tao Lin
  • Bio
  • News
  • Research
  • Publications
  • Talks
  • Experience
  • Prospective Students
  • Recent & Upcoming Talks
    • Example Talk
  • Conference Publications
    • Learning a Game by Paying the Agents
    • Learning to Play Multi-Follower Bayesian Stackelberg Games
    • A Unified Approach to Submodular Maximization Under Noise
    • Generalized Principal-Agent Problem with a Learning Agent
    • Information Design with Unknown Prior
    • User-Creator Feature Polarization in Recommender Systems with Dual Influence
    • Bias Detection via Signaling
    • Multi-Sender Persuasion: A Computational Perspective
    • Learning Thresholds with Latent Values and Censored Feedback
    • Sample Complexity of Forecast Aggregation
    • From Monopoly to Competition: Optimal Contests Prevail
    • Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions
    • How Many Representatives Do We Need? The Optimal Size of a Congress Voting on Binary Issues
    • Learning Utilities and Equilibria in Non-Truthful Auctions
    • A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling
    • Private Data Manipulation in Optimal Sponsored Search Auction
  • Working Papers
    • Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective
    • On the Coordination of Value-Maximizing Bidders
    • Information Design With Large Language Models
    • WOMAC: A Mechanism For Prediction Competitions
    • Explainable Information Design
    • Learning to Coordinate Bidders in Non-Truthful Auctions
  • Journal Publications
    • Information Design with Large Language Models: An Annotated Reading List
    • Generalized Principal-Agent Problem with a Learning Agent
    • From Monopoly to Competition: When Do Optimal Contests Prevail?
  • Recent & Upcoming Talks
    • Non-Bayesian Information Design: Learning and LLM-Based Approaches
    • Information Design with Large Language Models
    • Learning to Coordinate Bidders in Non-Truthful Auctions
    • How to Avoid Polarization in Recommender Systems with Dual Influence?
    • Bayesian Persuasion with a Learning Agent
    • Generalized Principal-Agent Problem with a Learning Agent
    • Private Data Manipulation in Sponsored Search Auctions
    • Sample Complexity of Forecast Aggregation
    • Persuading a Behavioral Agent: Approximately Best Responding and Learning
    • Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions
    • Robustness of Empirical Revenue Maximization in Auction Learning
  • Blog
    • For Prospective Students
  • Projects
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • News
    • title
  • Example_projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python
  • Notes
    • How Does Independence Help Generalization? Sample Complexity of ERM on Product Distributions
    • On Clearing Prices in Matching Markets: A Simple Characterization without Duality
  • Example_publications
    • An example preprint / working paper
    • An example journal article
    • An example conference paper
  • Tao Lin's Homepage

Reward Shaping for Inference-Time Alignment: A Stackelberg Game Perspective

Jan 31, 2026·
Haichuan Wang
,
Tao Lin
,
Lingkai Kong
,
Ce Li
,
Hezi Jiang
,
Milind Tambe
· 0 min read
PDF Cite
Last updated on Jan 31, 2026
LLM AI Alignment Principal-Agent Problem
On the Coordination of Value-Maximizing Bidders Nov 7, 2025 →

© 2026. This work is licensed under CC BY NC ND 4.0

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.