Scientific Hypothesis Generation

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 125% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 66

All topics

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents
Jun 30, 2026Keyu Zhao, Lingyan Kong, Fengli Xu +1Multi-Agent LLM Systems AI Agents for Scientific Discovery
Department of Electronic Engineering, Tsinghua University.
Evidence-Informed LLM Beliefs for Continual Scientific Discovery
Jun 28, 2026Dhruv Agarwal, Reece Adamson, Andrew McCallum +3Scientific Hypothesis Generation Belief Updating in LLMs
University of Massachusetts Amherst · Allen Institute for AI
Socratic agents for autonomous scientific discovery in high-dimensional physical systems
Jun 25, 2026Xianrui Zeng, Pengfei Liu, Yirui Zang +5Scientific Hypothesis Generation Autonomous Scientific Discovery
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, China. · Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Shanghai, 201800, China. · Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, 200433, China. +1
AI Scientists as Engines of Discovery: A Case for Development within Reformed Institutions
Jun 22, 2026Raul Jimenez, Boris Bolliet, Francisco Villaescusa-Navarro +7AI Agents for Scientific Discovery Scientific Hypothesis Generation
Institute of Cosmos Sciences (ICCUB), University of Barcelona, Barcelona, Spain · ICREA, Barcelona, 08010, Spain · Cavendish Astrophysics, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK +10
Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
Jun 12, 2026Li Xia, Baoxun WangScientific Hypothesis Generation Large Language Model-Guided Scientific Discovery
School of Economics and Management, Tsinghua University · Platform & Content Group, Tencent
Towards Diverse Scientific Hypothesis Search with Large Language Models
Jun 9, 2026Haorui Wang, Parshin Shojaee, Kazem Meidani +7Automated Algorithm Discovery Scientific Hypothesis Generation
Georgia Institute of Technology · Virginia Tech · Carnegie Mellon University +3
Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts
Jun 8, 2026Xu Li, Hanzhe Tu, Xun HanGraph Retrieval-Augmented Generation Scientific Hypothesis Generation
Southwest Petroleum University, Chengdu, Sichuan, China · Sichuan Police College, Luzhou, Sichuan, China
DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations
Jun 7, 2026Lei Lin, Ronghao Wang, Chunbao Zhou +2Scientific Reasoning Scientific Hypothesis Generation
Computer Network Information Center, Chinese Academy of Sciences, China
Contemporary AI lacks the imagination to diverge or negate in science
Jun 6, 2026Honglin Bao, Siyang Wu, Xiao Liu +3LLM-as-a-Judge Scientific Reasoning
Data Science Institute, University of Chicago · Knowledge Lab, University of Chicago
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates
Jun 2, 2026Paiheng Xu, Jing Liu, Wei AiScientific Hypothesis Generation Computational Social Science
University of Maryland, College Park
EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
May 29, 2026Xu Li, Hanzhe Tu, Xinyi Li +3Scientific Hypothesis Generation Research Idea Generation
Southwest Petroleum University, Chengdu, China · Sichuan Police College, Luzhou, China
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
May 28, 2026A. J. Lew, Y. Cao, M. J. BuehlerLLM Evaluation Scientific Reasoning
Unreasonable Labs · Unreasonable Labs Mountain View, CA 94043, USA
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
May 28, 2026Hongran An, Zonglin YangScientific Hypothesis Generation Human-in-the-Loop AI
Central Conservatory of Music · Nanyang Technological University
AI Research Agents Narrow Scientific Exploration
May 27, 2026Yixuan Tang, Yi YangAI Agents for Scientific Discovery AI Agent Evaluation
1*ISOM, The Hong Kong University of Science and Technology.
The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
May 26, 2026Shashwat Sourav, Viktoriia Baibakova, Sanjay Das +4LLM Grounding LLM Reasoning with Graphs
1Washington University in St. Louis · 2Oak Ridge National Laboratory · 3Lawrence Berkeley National Laboratory +1
Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?
May 26, 2026Qingyuan Zeng, Ziyang Chen, Pengxiang Cai +5Evidence-Grounded Reasoning Scientific Hypothesis Generation
The Hong Kong University of Science and Technology (Guangzhou) · Guangzhou University of Chinese Medicine
Hypothesis Generation and Inductive Inference in Children and Language Models
May 23, 2026Jeffrey Qin, Wasu Top Piriyakulkij, Zhuangfei Gao +4Bayesian Inference Scientific Hypothesis Generation
Computer Science University of Waterloo · Department of Computer Science Cornell University · Department of Computer Science Dalhousie University +1
LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
May 21, 2026Sanchit Kabra, Nikhil Abhyankar, Saaketh Desai +2Scientific Discovery Scientific Hypothesis Generation
1Virginia Tech · 2Sandia National Laboratories
EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery
May 20, 2026Xiaoyu Xiong, Yuqi Ren, Deyi XiongScientific Hypothesis Generation Multi-Agent Collaboration
TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China
Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine
May 18, 2026Christiaan G. A. Viviers, Koen de Bruin, Mirre M. Trines +6Scientific Hypothesis Generation Evidence-Grounded Generation
ARIA Lab, Signal Processing Systems, Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. · Laboratory of Chemical Biology, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. · The Louis Family Laboratory for Targeted Drug Delivery and Personalized Medicine Technologies, Department of Chemical Engineering, Technion - Israel Institute of Technology, Haifa, Israel. +2
Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
May 14, 2026Songyang Gao, Yinghui Xia, Siyi Liu +1Scientific Hypothesis Generation Research Idea Generation
The Hong Kong University of Science and Technology (Guangzhou) · Tsinghua University · The Hong Kong University of Science and Technology
LLM Jaggedness Unlocks Scientific Creativity
May 11, 2026Shray Mathur, J. Anibal Boscoboinik, Esther H. R. Tsai +1Creativity Assessment LLM Evaluation
Center for Functional Nanomaterials, Brookhaven National Laboratory Upton, NY 11973, USA
Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery
May 9, 2026Harshit Bisht, Vinay Kumar, Kevin Maik Jablonka +2AI Agents for Scientific Discovery Scientific Hypothesis Generation
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi · Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena · Center for Energy and Environmental Chemistry Jena, Friedrich Schiller University Jena +3
LLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy Experiments
May 7, 2026Boris Slautin, Utkarsh Pratiush, Yu Liu +2Scientific Hypothesis Generation Large Language Model-Guided Scientific Discovery
Department of Materials Science and Engineering, University of Tennessee, Knoxville, TN 37923, USA
More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation
May 7, 2026Jie Yu, Song QiuAI for Science Scientific Hypothesis Generation
Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai, 200241
Hypothesis generation and updating in large language models
May 7, 2026Hua-Dong XiongLogical Reasoning Bayesian Inference
School of Psychological and Brain Sciences Georgia Tech
Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation
May 6, 2026Jiangwen Dong, Bo Li, Wanyu LinMulti-Agent LLM Systems Scientific Hypothesis Generation
1The Hong Kong Polytechnic University · 2The Hong Kong University of Science and Technology
An explainable hypothesis-driven approach to Drug-Induced Liver Injury with HADES
May 4, 2026Maciej Wisniewski, Bartosz Topolski, Pawel Dabrowski-Tumanski +2Explainable Artificial Intelligence AI Agents for Scientific Discovery
Ingenix.ai, Warsaw, Poland · Laboratory of Bioinformatics and Computational Genomics, Warsaw University of Technology, Warsaw, Poland · Laboratory of Functional and Structural Genomics, Centre of New Technologies, University of Warsaw, Warsaw, Poland
Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output
May 1, 2026James Mooney, Zae Myung Kim, Young-Jun Lee +1AI Agents for Scientific Discovery Scientific Hypothesis Generation
University of Minnesota
A phenotype-driven and evidence-governed framework for knowledge graph enrichment and hypotheses discovery in population data
Apr 18, 2026Adela Bâra, Simona-Vasilica OpreaScientific Hypothesis Generation Knowledge Graphs
Department of Economic Informatics and Cybernetics, Bucharest University of Economic Studies, Bucharest, Romania

Jun 30, 2026, cs.AIJ/K move · Enter open · S save

Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents

Keyu Zhao, Lingyan Kong, Fengli Xu, Yong Li

Department of Electronic Engineering, Tsinghua University.

Multi-Agent LLM Systems AI Agents for Scientific Discovery Scientific Hypothesis Generation LLM Agent Training Synthetic Data Generation for Language Models

Open paper AskPDF arXiv

Ideation plays a pivotal role in scientific discovery. Recent LLM, especially AI Scientist systems, show promising potential for automated ideation. However, existing approaches predominantly rely on pre-defined agentic workflows. This constraint severely limits the flexibility required to navigate the vast search space of scientific literature and the complex action space of research reasoning. Recently, training Agentic LLMs has emerged as a promising direction, offering flexible reasoning frameworks and the capability for autonomous tool utilization. However, there remains a non-trivial challenge: applying previous agentic data synthesis methods to scientific ideation suffers from prohibitively high data synthesis cost. To bridge this gap, we propose Agentic-Ideation, a novel framework comprising an automated trajectory synthesis pipeline and a specialized agentic LLM trained for scientific ideation. Specifically, we first define a comprehensive tool space incorporating three external tools and three cognitive tools. Then we introduce an Oracle-Guided Data Synthesis strategy. By leveraging a reference idea as oracle guidance, this approach steers the multi-agent system to efficiently reconstruct the logical reasoning and tool invocation paths, transforming aimless trial-and-error into directed trajectory generation. Finally, we train the agent on these synthesized trajectories, employing a masking strategy on tool execution results. This ensures the model focuses on decision-making logic without interference from external feedback. Experimental results demonstrate that our method outperforms the SOTA workflow-based baseline by \textbf{11.91%} in overall quality. Furthermore, our approach improves the sample efficiency of high-quality data synthesis by \textbf{over 10

\times

Momentum

Related topics

Latest papers 66