11 papers
Cold-Start Personalization via Training-Free Priors from Structured World Models
Avinandan Bose, Shuyue Stella Li, Faeze Brahman +6
Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available. The core challenge is a routing problem: each…
Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics
Sunmook Choi, Yahya Sattar, Yassir Jedra +2
We study a nonstationary bandit problem where rewards depend on both actions and latent states, the latter governed by unknown linear dynamics. Crucially, the state dynamics also d…
PrefDisco: Benchmarking Proactive Personalized Reasoning
Shuyue Stella Li, Avinandan Bose, Faeze Brahman +4
Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment t…
LoRe: Personalizing LLMs via Low-Rank Reward Modeling
Avinandan Bose, Zhihan Xiong, Yuejie Chi +3
Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning fr…
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…
Sub-optimality of the Separation Principle for Quadratic Control from Bilinear Observations
Yahya Sattar, Sunmook Choi, Yassir Jedra +2
We consider the problem of controlling a linear dynamical system from bilinear observations with minimal quadratic cost. Despite the similarity of this problem to standard linear q…