The paper introduces Think‑Probe‑Respond (TPR), a lightweight method to improve large language models’ ability to judge the novelty of research ideas. It identifies a systematic bias where models tend to label ideas as "medium novel" despite generating human‑like rationales, and shows that probing hidden states during reasoning and conditioning the final response on these probes boosts novelty judgment accuracy by 22.30%. TPR effectively reduces the medium‑novelty bias across strong baseline models.
By Tim Schopf, Tobias Schreieder, Akiko Aizawa
arXiv:2604. 15145v2 Announce Type: replace Abstract: The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task.
By Miri Liu, ChengXiang Zhai
arXiv:2607. 26066v1 Announce Type: cross Abstract: The growing volume of scientific submissions has motivated interest in using large language models (LLMs) to assist peer review.
By Ranjitha Shivaprasad Ballakuraya, Arash Mahyari, Ashok Srinivasan
NovGauge is a new benchmark designed to diagnose large language models’ ability to assess scientific paper novelty. It contains 619 paper pairs and 50 multi-paper sets, each labeled along three dimensions—task, problem, and method—by experts from ICLR reviewer overlap claims and survey co-citations. The study evaluates 18 LLMs, revealing high hallucination rates and weak evidence grounding, with the best model achieving only 43‑72% verified F1 across dimensions.
By Guoqiang Zhang, Kexin Tan, Ming Zhang, Li Ju, Wenqing Jing, Zhonghan Yue, Jiayi Chen, Shiqiang Wu, Shaofan Liu, Yue Zhang, Yuankai Ying, Yang Shi, Tao Gui, Qi Zhang, Xuanjing Huang
arXiv:2607. 01233v1 Announce Type: cross Abstract: LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert preference.
By Ziyu Chen, Yilun Zhao, Arman Cohan
arXiv:2609.14057v1 Announce Type: new
Abstract: Frontier LLMs are increasingly capable of conducting automated research, yet their creativity in this setting has not been systematically evaluated. In...
By Yiheng Zhao, Mengzhuo Chen, Chengming Hu, Pengyi Liao, Yiran Pang
arXiv:2606. 08251v1 Announce Type: cross Abstract: Bold projections that artificial intelligence will accelerate scientific discovery have raced ahead of evidence from working scientists, and the field still lacks large-scale, scientist-in-the-loop tests of these claims.
By Honglin Bao, Siyang Wu, Xiao Liu, Sida Li, Shiyun Cao, James A. Evans
arXiv:2608. 16795v1 Announce Type: cross Abstract: Systems that generate scientific research questions are evaluated today by expert scores, LLM-as-judge ratings, or curated case studies -- all subjective, none falsifiable.
By Hui Mao
arXiv:2606. 26130v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting remain unclear.
By Francesca Carlon, Brecht Verbeken, Vincent Ginis, Andres Algaba
arXiv:2603.20884v4 Announce Type: replace
Abstract: To alleviate the heavy burden of paper screening, researchers increasingly rely on existing AI agents, such as AI reviewers or DeepResearch, for pa...
By Jiajun Hou, Hexuan Deng, Wenxiang Jiao, Xuebo Liu, Xiaopeng Ke, Derek F. Wong, Min Zhang
The paper "Learning to Ideate for Scientific Impact" explores using delayed signals of scientific uptake—specifically citation-normalized impact—as feedback to steer large language models toward generating high‑impact research ideas. The authors build a dataset of over 100,000 computer science papers, train a reward model to predict citation impact from goal‑idea pairs, and align an idea generator via supervised fine‑tuning and reinforcement learning. Evaluation with a reference‑grounded protocol shows that the RL‑tuned model consistently produces ideas with higher estimated impact than baseline models.
By Shubham Kale, Aniketh Garikaparthi, Manasi Patwardhan
arXiv:2607. 05682v1 Announce Type: new Abstract: LLM systems for scientific discovery increasingly assist with ideation, literature synthesis, experiment planning, and report generation, but the first research question they propose can remain difficult to audit: it may sound plausible without exposing the mechanism, falsifier, or assumption that a scientist should inspect.
By Yufeng Wang