← Back to all news
arXiv AI

Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery

Principia is an LLM-based framework that constructs and refines scientific principles during test-time discovery. It generates comparative causal hypotheses from related inputs and outcomes, synthesizes recurring relationships into inductive principles, and iteratively updates these principles as new observations are obtained. Across benchmarks in molecular optimization, protein engineering, gene perturbation, and molecular property prediction, Principia outperforms baselines that rely on internal knowledge, external sources, or experience summaries, producing plausible principles consistent with scientific literature.

Related stories

arXiv Computation and Language
Oct 19

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

The paper introduces DiscoveryRSI, a framework that recursively learns to generate valuable scientific hypotheses by building hypothesis trees through multi‑agent evolutionary search, compiling investigations into executable tasks, and refining the process via credit optimization, replay, and rediscovery. It also presents DFM‑Bench, a benchmark for assessing hypothesis quality across multiple dimensions. Experiments in four life‑science domains show that the system improves hypothesis quality, particularly in falsifiability and data resolvability, and outperforms other large‑language‑model agents in expert evaluations.

By Jianyuan Zhong, Chenwei Wu, Zhaochen Yu, Xixian Jiang, Xuewei Li, Hao Xiao, Xilin Dai, Junyang Wang, Jiaru Zou, Zhiqing Cui, Boyuan Zheng, Jing Xiong, Zhen Zhang, Qiang Gao, Michael Morley, Luis Nakayama, Qiang Xu, Liyue Shen, Tao Gui, Leo Anthony Celi, James Zou, Zhenfei Yin, Yingcheng Wu, Ling Yang
llmsagents
More like this →
arXiv Machine Learning
Sep 22

Tool-Augmented On-Policy Distillation for LLM Domain Adaptation in Sequence-Based Omics Tasks

The paper introduces OmicsBench, a new reasoning benchmark for multi‑omics sequences that includes 1,160 expert‑validated questions across DNA regulation, RNA processing, and protein function tasks, requiring traceable evidence chains. Evaluation of 17 large language models shows that scientific LLMs, while more accurate in classification, often lack valid evidence, suggesting shortcut learning. To address this, the authors propose tool‑augmented on‑policy distillation (TA‑OPD), a post‑training method that improves both evidence grounding and predictive performance across five Qwen3.5 models of varying sizes.

By Jie Ying, Zhefan Wang, Zihong Chen, Zhengqing Li, Jinzhe Li, Gang Li, Jian Liu, Fang Hu, Tao Luo, Zhonghang Yuan, Wanli Ouyang, Stan Z. Li, Fan Yang, Nanqing Dong
llmsfine-tuningefficiencybenchmarks
More like this →
arXiv Computation and Language
Sep 14

HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge

The paper introduces HypoKG, a unified biochemical knowledge graph built from KEGG, Rhea, and UniProt, and uses it to benchmark 13,200 biomedical hypotheses generated by six large language models (LLMs). By varying the biological information provided—source enzyme only, full biological path, or source and disease endpoint—the study finds that LLMs produce higher-scoring hypotheses when given minimal information, but these are less evidence‑grounded. When supplied with the full biological path, the models generate hypotheses that align more closely with known mechanistic relationships, a phenomenon the authors term evidence‑disciplined reasoning, which is confirmed by shuffling intermediate path steps. "whyItMatters":"The study demonstrates that knowledge graphs can both uncover novel disease–enzyme pairs and guide LLMs to reason more accurately from evidence, improving the reliability of AI‑generated biomedical hypotheses."

By Dominic Okonkwo, Adetayo Okunoye, Ismailcem Budak Arpinar
llmsbenchmarks
More like this →
arXiv AI
Sep 7

Hakken: Predicting future discoveries to fill the gaps in today's knowledge

Hakken is a domain‑agnostic system that predicts and explains future scientific discoveries by combining transformer‑based models trained on temporal knowledge graphs with large language model semantic knowledge. It identifies novel relationships between scientific concepts that extend beyond the deductive hull of existing knowledge and provides explanations to help scientists assess these predictions. In the biomedical domain, Hakken set a new benchmark for time‑aware multi‑label relation prediction, generated 1.5 million high‑confidence hypotheses about aging, and experimentally confirmed two predictions that revealed previously undocumented interactions relevant to drug discovery.

By Tarek R. Besold, Uchenna Akujuobi, Pablo Sanchez, Alessandra Toniato, Kana Maruyama, Jihun Choi, Samy Badreddine, Frederick Gifford, Daniel Evans-Yamamoto, Sucheendra K. Palaniappan, Miquel Ferrer, Kae Nagano, Iris Rossell, Tom Joy, Hatem ElShazly, Chrysa Iliopoulou, Christoph Wehner, Thiviyan Thanapalasingam, Susana Nunes, Pedro G. Cotovio, Peter Wurman, Peter Stone, Hiroaki Kitano, Michael Spranger
llmsbenchmarks
More like this →
arXiv AI
Oct 7

Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space

The paper introduces an experimental model‑class revision framework that jointly proposes structural edits to a hypothesis space and diagnostic experiments to test those edits. By coupling a class‑level distinguishability objective with anytime‑valid sequential evidence, the method only revises the model class after the current one is rejected. On 400 controlled dynamical environments, the approach achieves 89.5% exact recovery with 32 experiments, outperforming baselines and transferring well to unseen mechanisms, library insufficiency detection, and other benchmark tasks.

By SiYuan Ma, Albert Gao, Chunzheng Zhu, Xin Yan, Wenlong Zhang, Wenxin Zhang, Luqi Gong, Tianlin Li, Qixin Zhang
More like this →