3 papers
cs.LG2026
Over-Searching in Search-Augmented Large Language Models
Roy Xie, Deepak Gopinath, David Qiu +4
Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. However, they often over-search -- unnecessarily invoking search…
cs.CL2026
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Roy Xie, David Qiu, Deepak Gopinath +5
Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increa…
cs.AI2025
ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry
Zhiyuan Huang, Baichuan Yang, Zikun He +5
Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often relying on simple image-text pairs…