8 papers · 1 filter
Cogentic: Multi-Agent Orchestration for Automated Proof Discovery
Yang Cai, Vineet Gupta, Yanchen Jiang +4
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a singl…
Efficiency of Generalized Proportional First-Price Auctions Under Auto-bidding
Yang Cai, Vineet Gupta, Yanchen Jiang +4
Auto-bidding is now widely adopted in online advertising platforms, allowing advertisers to specify high-level campaign objectives--such as maximizing total value subject to a retu…
Efficient Online Inverse Optimization with Regret
Yang Cai, Anupam Gupta, Vineet Gupta +7
We give a deterministic algorithm for online inverse linear optimization with regret , uniform in the horizon and time per round. A bound of this order was obtaine…
Accelerating Min-Max Optimization via Power-Law Stepsizes
Yue Wu, Weiqiang Zheng, Yang Cai +1
We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization. It is known that EG with a fixed stepsize achieves a $Θ(T^{-…
Last-Iterate Convergence of Anchored Gradient Descent
Yang Cai, Weiqiang Zheng
We study the monotone inclusion problem , where is monotone and Lipschitz, and is maximally monotone, a framework that encompasses monotone variational ineq…
A New Lower Bound for the Random Offerer Mechanism in Bilateral Trade using AI-Guided Evolutionary Search
Yang Cai, Vineet Gupta, Zun Li +1
The celebrated Myerson--Satterthwaite theorem shows that in bilateral trade, no mechanism can be simultaneously fully efficient, Bayesian incentive compatible (BIC), and budget bal…
Is Online Linear Optimization Sufficient for Strategic Robustness?
Yang Cai, Haipeng Luo, Chen-Yu Wei +1
We consider bidding in repeated Bayesian first-price auctions. Bidding algorithms that achieve optimal regret have been extensively studied, but their strategic robustness to the s…
Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
Yang Cai, Weiqiang Zheng
Aligning large language models (LLMs) to serve users with heterogeneous and potentially conflicting preferences is a central challenge for personalized and trustworthy AI. We forma…