SciDocBench is a workflow-centered benchmark for scientific document understanding that includes 124 expert-authored questions across seven capability groups and 19 subtasks in five scientific domains. Each question is evaluated under four conditions—English or Chinese, all-images-first or interleaved document representations—resulting in 496 evaluation instances. The benchmark is paired with SciDocIR, a typed evidence-graph representation, and SciDocDataset, a collection of 15K fine-tuning and 8K reinforcement-learning samples, forming an evaluation-to-training framework for scientific-document assistants.
By Shenxi Wu, Yuhong Liu, Haosong Zhang, Tongjin Zou, Yanxun Zhang, Gaochang Chen, Dun Liang, Jiaqi Wang, Zhecan James Wang, Yuhang Zang, Dahua Lin
arXiv:2606. 04579v1 Announce Type: new Abstract: While Process Reward Models (PRMs) have achieved remarkable success in mathematical reasoning, their application in complex scientific domains-such as biology, chemistry, and physics remains largely unexplored.
By Xiangyu Zhao, Hengyuan Zhao, Yiheng Wang, Wanghan Xu, Yuhao Zhou, Qinglong Cao, Zhiwang Zhou, Lei Bai, Wenlong Zhang, Xiao-Ming Wu
arXiv:2607. 02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete information.
By Shengyi Hua, Kangzhe Hu, Conghui He, Xiaofan Zhang, Shaoting Zhang
arXiv:2608.30109v1 Announce Type: new
Abstract: Large Language Models (LLMs) trained on extensive scientific research are increasingly integrated as assistants for scientific discovery. However, most...
By Shrinidhi Kumbhar Santosh Mashetty Divij Handa Kevin Coutinho, Siddharth Sambhaji Ghule, Chitta Baral
arXiv:2606. 28277v1 Announce Type: cross Abstract: Artificial intelligence is driving a revolution in scientific discovery, accelerating everything from hypothesis generation to mathematical theorem proving.
By Rajesh Jayaram, Drew Tyler, David Woodruff, Corinna Cortes, Yossi Matias, Vahab Mirrokni, Vincent Cohen-Addad
The paper introduces BioCheck Agent, an LLM-based system that generates structured biomedical fact‑checking reports using agentic search and a reinforcement‑learning framework called EG‑GRPO. Unlike prior methods that output only supported or refuted labels, BioCheck Agent synthesizes conclusions with retrieved evidence from PubMed, employing advanced Boolean search operators. Experiments show that, compared to the base Qwen3.5‑4B model, BioCheck Agent improves label prediction accuracy on SciFact by 9.95 %, raises evidence quality by 3.7 %, and reduces hallucinations by 19.63 %.
By Jiongxiao Wang, Dingli Ma, Chaoqun Ni
arXiv:2608.30214v1 Announce Type: new
Abstract: Scientific reasoning remains challenging for open-source models, largely due to the lack of high-quality scientific reasoning data. Existing datasets a...
By Yu Li, Wei Li, Xin Gao, Mengyuan Sun, Xiaoyang Wang, Qizhi Pei, Lijun Wu
The paper introduces Reinforced Adversarial Learning (RAL), a method that uses a co‑trained LLM judge to transform reference answers into a reward signal for on‑policy post‑training of reasoning LLMs. RAL is validated on three verifiable tasks—integer multiplication, code‑based arithmetic‑expression synthesis, and SMILES‑to‑formula translation—showing performance comparable to reinforcement learning with verifiable rewards. The approach is further applied to scientific abstract generation, producing abstracts that are harder to distinguish from real ones than those from frontier‑LLM baselines, demonstrating its potential for high‑value domains where explicit reward signals are hard to define.
By Albert Bou, Javier Valdes-Aleman, Jon M. Laurent, Samuel G. Rodriques, Andrew D. White, Michaela Hinks, Siddharth Narayanan
The paper introduces Proof-of-Use (PoU), a reinforcement learning framework designed to prevent tool‑call hacking in deep research agents. PoU enforces evidence grounding by requiring agents to cite normalized evidence identifiers and uses a multi‑objective reward system that includes progressive process rewards, an answer‑support alignment reward, and a curriculum‑style adaptive reward mixing. Experiments demonstrate that PoU effectively mitigates tool‑call hacking and promotes robust, adaptive tool usage even under domain and tool shifts.
By Shengjie Ma, Chenlong Deng, Jiaxin Mao, Jiadeng Huang, Teng Wang, Junjie Wu, Changwang Zhang, Jun wang
arXiv:2608.28612v1 Announce Type: new
Abstract: Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between domain reasoning and factual groun...
By Xuerui Su, Liya Guo, Qizhi Pei, Qipeng Guo, Zhongbo Tian, Lijun Wu, Kai Chen, Zun Wang
arXiv:2604. 13201v2 Announce Type: replace-cross Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging.
By Oliver Bentham, Vivek Srikumar
arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.
By Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su, Hongru Hou, Hengrui Chen, Ao Xu, Deqing Yang