Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve fit; and learning such a model requires \emph{experiments}, because passive data leaves its mechanisms unidentified. Experiments are expensive, so the central problem is \emph{data efficiency}.
arXiv:2602. 18266v2 Announce Type: replace Abstract: Automated methods for discovering mechanistic simulator models from observational data offer a promising path toward accelerating scientific progress.
By Stefan Wahl, Raphaela Schenk, Ali Farnoud, Jakob H. Macke, Daniel Gedon
arXiv:2606. 29315v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on parametric knowledge, fixed post-training data, retrieval, or search.
By Abhranil Chandra, Sankaran Vaidyanathan, Utsav Dhanuka, Varun Gandhi, Scott Niekum
The paper proposes a distributional theory explaining how large language models (LLMs) incorporate external evidence into their decision-making process. It identifies three key predictions: (1) evidence is more persuasive when it aligns with the model’s prior beliefs, (2) models more readily accept errors from their own internal processes than from external sources, and (3) the same evidence can improve weaker models while harming stronger ones. Extensive experiments across ten million trials, twelve LLMs from four families, and eight domains—including quantum mechanics, physics, genetics, and molecular biology—confirm these predictions and reveal that evidence integration occurs late in the network as a structured sequence of steps rather than through a simple trust metric.
By Sebastien Kawada, Manolis Kellis
arXiv:2608. 15669v1 Announce Type: new Abstract: Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs.
By Zhongwei Yu, Yan Song, Xue Yan, Anjie Liu, Xingyu Lu, Yihang Chen, Huichi Zhou, Siyuan Guo, Luoyang Sun, Sihan Chen, Xiangning Yu, Jun Wang
arXiv:2609.38309v1 Announce Type: cross
Abstract: The search for physics Beyond the Standard Model (BSM) is generally limited not by the supply of theory descriptions but by the lack of discriminatin...
By Ibrahim Elsharkawy, Victoria Knapp-Perez, Wahid Bhimji, Aishik Ghosh
arXiv:2609.01526v1 Announce Type: new
Abstract: Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in...
By Qing Zhao, Haowei Li, Weijian Deng, Pengxu Wei, Liang Lin
arXiv:2606. 17516v1 Announce Type: cross Abstract: Causal discovery from observational data remains challenging due to the need to recover directed structure and latent confounding without interventions.
By Patrick Bl\"obaum, Krishnakumar Balasubramanian, Shiva Prasad Kasiviswanathan
arXiv:2605.26087v2 Announce Type: replace-cross
Abstract: Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of...
By Matt L. Wiemann, Lindsay M. Smith, Peter Melchior, Siddharth Mishra-Sharma, Andrew Gordon Wilson, Pavel Izmailov, Carolina Cuesta-L\'azaro
arXiv:2607. 13608v1 Announce Type: new Abstract: Automatic scientific discovery has long been a goal of computational scholars - a machine that can discover nature's secrets on its own, moving computational systems beyond data-fitting tools toward the generation and refinement of mechanistic models of the universe.
By David Krongauz, Arad Zulti, Eran Segal, Teddy Lazebnik
arXiv:2606. 29604v1 Announce Type: cross Abstract: We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes.
By Andrew Mack, Nina Panickssery, Alexander Matt Turner
arXiv:2608. 12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood.
By Mengru Wang, Junfeng Fang, Shuofei Qiao, Zhenqian Xu, Haoming Xu, Haoxiong Wang, Shumin Deng, Linyi Yang, Zhixiang Cui, Xin Xu, Yunzhi Yao, Buqiang Xu, Fei Shen, Haozhe Luo, Yunxiang Wei, Ningyu Zhang, Julian McAuley, Tat Seng Chua, Huajun Chen