From the 1 of 5 linked papers with an AI index.
5 papers
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
Rui Wang, Hongru Wang, Yi Chen +4
The paper investigates how on-policy distillation guides large language model students during training, identifies two main failure modes—student‑teacher mismatch and length exploi…
Geometry-Calibrated Conformal Abstention for Language Models
Rui Xu, Yi Chen, Sihong Xie +1
When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about…
How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews
Riley Grossman, Songjiang Liu, Michael K. Chen +3
Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generative AI disrupts web search by re…
WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models
Rui Wang, Ce Zhang, Jun-Yu Ma +10
The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, curr…
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Rui Wang, Hongru Wang, Boyang Xue +7
Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (Sy…