papers

Publications (173)

cs.AI2026

Step-level Optimization for Efficient Computer-use Agents

Jinbiao Wei, Kangqi Ni, Yilun Zhao +2

Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on br…

cs.CL2026

SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks

Yilun Zhao, Kaiyan Zhang, Tiansheng Hu +15

We present SciArena, an open and collaborative platform for evaluating foundation models on scientific literature-grounded tasks. Unlike traditional benchmarks for scientific liter…

cs.AI2026

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

Siyi Gu, Jialin Chen, Sophia Zhou +2

Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-t…

cs.CL2024

Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?

Xiangru Tang, Yiming Zong, Jason Phang +4

Despite the remarkable capabilities of Large Language Models (LLMs) like GPT-4, producing complex, structured tabular data remains challenging. Our study assesses LLMs' proficiency…

cs.CL2026

References Improve LLM Alignment in Non-Verifiable Domains

Kejian Shi, Yixin Liu, Peifeng Wang +3

While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking groun…

cs.IR2020

Ranking Significant Discrepancies in Clinical Reports

Sean MacAvaney, Arman Cohan, Nazli Goharian +1

Medical errors are a major public health concern and a leading cause of death worldwide. Many healthcare centers and hospitals use reporting systems where medical practitioners wri…