9 papers
DR Pixel: Page-Native Deep Research with Vision-Language Models
Tiansheng Hu, Yichuan Wang, James V. Talwar +3
Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-e…
BackTrend: Evaluating Scientific Weak-Signal Prediction via Backward Reconstruction
Xiao Zhou, Yilun Zhao, Owen Jiang +4
Scientific weak signals are early, low-visibility research directions that later become central to mature scientific topics, yet existing resources such as trend tracking, citation…
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
Sihong Wu, Owen Jiang, Yilun Zhao +5
Peer review is a multi-stage process involving reviews, rebuttals, meta-reviews, final decisions, and subsequent manuscript revisions. Recent advances in large language models (LLM…
RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
Sihong Wu, Yiling Ma, Yilun Zhao +4
Large language models (LLMs) are increasingly used across the scientific workflow, including to draft peer-review reports. However, many AI-generated reviews are superficial and in…
SAGE: Benchmarking and Improving Retrieval for Deep Research Agents
Tiansheng Hu, Yilun Zhao, Canyu Zhang +2
Deep research agents have emerged as powerful systems for addressing complex queries. Meanwhile, LLM-based retrievers have demonstrated strong capability in following instructions…
SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature
Hang Ding, Yilun Zhao, Tiansheng Hu +2
The accelerating growth of scientific publications has intensified the need for scalable, trustworthy systems to synthesize knowledge across diverse literature. While recent retrie…
FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain
Tiansheng Hu, Tongyan Hu, Liuyang Bai +3
Recent LLMs have demonstrated promising ability in solving finance related problems. However, applying LLMs in real-world finance application remains challenging due to its high ri…
FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answering
Yitao Long, Tiansheng Hu, Yilun Zhao +2
Large Language Models (LLMs) frequently hallucinate to long-form questions, producing plausible yet factually incorrect answers. A common mitigation strategy is to provide attribut…
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…