Scientific Discovery

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

28 new papers

A weekly snapshot of new work published in Scientific Discovery.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Scientific Discovery.

Period ending 2026-09-07

21 new papers

A weekly snapshot of new work published in Scientific Discovery.

Inside this field

Focused directions

Focused topic

Scientific Discovery

Within Scientific Discovery

408 papersExplore

Focused topic

Autoresearch

Within Scientific Discovery

181 papersExplore

Focused topic

Artificial Intelligence Scientists

Within Scientific Discovery

72 papersExplore

Focused topic

Scientific Workflows

Within Scientific Discovery

58 papersExplore

Focused topic

Artificial Intelligence Research

Within Scientific Discovery

51 papersExplore

Focused topic

Scientific Agents

Within Scientific Discovery

46 papersExplore

720 papers

Latest in Scientific Discovery

Browse all topics →

The Case for Model Science: Verify, Explore, Steer, Refine
May 31, 2026Przemyslaw Biecek, Luca Longo, Jianlong Zhou +3Artificial Intelligence Models Scientific Discovery
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
May 31, 2026Teddy Ferdinan, Bartłomiej Koptyra, Mikołaj Langner +42Scientific Discovery Large Language Model Reasoning
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery
May 30, 2026Tyler H. McCormickScientific Discovery Mechanistic Interpretability
Toward Responsible and Epistemically Grounded Multilingual LLMs for Computational Social Science and Humanities
May 30, 2026Wajdi ZaghouaniMultilingual Reasoning Multilingual Large Language Models
AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle
May 29, 2026Weitong Qian, Beicheng Xu, Zhongao Xie +16Scientific Agents Scientific Workflows
KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning
May 29, 2026Dominik Soós, Meng Jiang, Jian WuScientific Discovery Headlines
Reading Between the Citations: A Typed Claim Network for Scientific Literature
May 29, 2026Ning Ding, Sergio J. Rodríguez Méndez, Pouya G. OmranCitations Knowledge Graphs
Extending AI for Research to the Humanities: A Multi-Agent Framework for Evidence-Grounded Scholarship
May 29, 2026Yating Pan, Jiajun Zhang, Jun Wang +1Autoresearch Human Oversight
MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials
May 29, 2026Etinosa Osaro, Santosh Adhikari, Stamatia Zavitsanou +2Interatomic Potentials Autoresearch
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
May 28, 2026Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6Scalable Vector Graphic Human-Agent Collaborative Paper-To-Page
Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software
May 28, 2026Nhat-Minh NguyenArtificial Intelligence Scientists Scientific Agents
COMPOSE: Composing Future Theorems from Citations and Formal Structure
May 28, 2026David Busbib, Michael WermanCitations Formalization
SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
May 28, 2026Sy-Tuyen Ho, Minghui Liu, Huy Nghiem +1Artificial Intelligence Scientists Provable Guarantees
Self-Trained Verification for Training- and Test-Time Self-Improvement
May 28, 2026Chen Henry Wu, Aditi RaghunathanSelf-Training Recursive Self-Improvement
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
May 28, 2026A. J. Lew, Y. Cao, M. J. BuehlerScientific Discovery Artificial Intelligence Scientists
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
May 28, 2026Wanghan Xu, Shuo Li, Tianlin Ye +48Autoresearch Agentic Benchmarks
Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
May 28, 2026Víctor GallegoAutoresearch Self-Play
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
May 28, 2026Yiming Liu, Bin Lu, Meng Jin +6Geological Semantic Understanding Ocean
OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields
May 28, 2026Wanhao Liu, Jiaqing Xie, Qian Tan +10Materials Science Multimodal Reasoning Benchmarks
AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation
May 28, 2026Idris Abdulmumin, Tajuddeen Gwadabe, Shamsuddeen Hassan Muhammad +11African Languages Translation Quality
DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation
May 28, 2026Ziyue Yang, Da Ma, Hanqi Li +8Citations Survey
MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
May 28, 2026Hongran An, Zonglin YangHypothesis Generation Scientific Discovery
SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing
May 28, 2026Almene De Meran Meguimtsop, Maria Leonor Pacheco, Daniel E. AcunaAcademic Integrity Scientific Discovery
Attention Asymmetry in AI Layoff Discourse on X: A Computational Analysis of Capital vs Labour Amplification
May 28, 2026Joy BoseDiscourse Asymmetry
Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
May 27, 2026Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat +3Symbolic Regression Scientific Discovery
First head-to-head comparison of agentic AI applied to the analysis of simulated data of the Einstein Telescope
May 27, 2026Gianluca IngugliaArtificial Intelligence Scientists Agentic Workflows
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
May 27, 2026Shanghua Gao, Ada Fang, Marinka ZitnikScientific Agents Artificial Intelligence Agents
ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
May 27, 2026Yihan Xia, Taotao WangAutoresearch Academic Papers
AI Research Agents Narrow Scientific Exploration
May 27, 2026Yixuan Tang, Yi YangArtificial Intelligence Scientists Ideas
AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
May 27, 2026Ruiyi Zhang, Peijia Qin, Qi Cao +2Artificial Intelligence Models Scientific Discovery
MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents
May 27, 2026Thao Nguyen, Heng JiStructure-Based Drug Design Autoresearch
QSignAI: Quantum-Randomness-Seeded Identity Signatures at the Intersection of AI for Science and Science for AI
May 26, 2026Dongping Liu, Aoyu Zhang, Luyao ZhangQuantum Machine Learning Human-Ai Interaction
DeepSciVerify: Verifying Scientific Claim--Citation Alignment via LLM-Driven Evidence Escalation
May 26, 2026Shaghayegh Sadeghi, Khashayar Khajavi, Rise Adhikari +1Noisy Claim Verification Citations
CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text
May 26, 2026Khashayar Khajavi, Shaghayegh Sadeghi, Rise Adhikari +1Citations Scientific Discovery
Eliot: Interactively $\underline{E}$ xploring Fast-Changing Scientific $\underline{Li}$ terature Trends with $\underline{O}$ nline Da $\underline{t}$ a and Learning
May 26, 2026Bernardo A. Denkvitts, Nitin Gupta, Biplav SrivastavaReal Datacite Dois Scientific Discovery
When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery
May 26, 2026Neel Tushar Shah, Manglam KartikArtificial Intelligence Scientists Verifier
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
May 26, 2026Siddharth Chaini, Federica B. Bianco, Ashish MahabalPhase-Folded Light Curves Gaussian Process
Maat: The Agentic Legal Research Assistant for Competition Protection
May 26, 2026Basant Mounir, Farida Madkour, Amira Abdelaziz +1Legal Domain Agentic Search
The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
May 26, 2026Shashwat Sourav, Viktoriia Baibakova, Sanjay Das +4Knowledge Graphs Hypothesis Generation
Persistent AI Agents in Academic Research: A Single-Investigator Implementation Case Study
May 26, 2026Anas H. AlzahraniAgent Memory Artificial Intelligence Agents
AI evaluation may bias perceptions: The importance of context in interpreting academic writing
May 26, 2026Shang Wu, Randol YaoArtificial Intelligence Evaluation Writing
Can LLMs extract scientific consensus? A case study in high-temperature superconductivity
May 26, 2026Mouyang Cheng, Wenhao He, Zhuotao Jin +9Scientific Discovery Case Study
A Systematic Study of Behavioral Cloning for Scientific Data Annotation
May 26, 2026Ishaan Singh Chandok, Core Francisco ParkBehavior Cloning Annotations
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
May 25, 2026Rui Meng, Bhavana Dalvi Mishra, Jiefeng Chen +10Autoresearch Scientific Agents
MULTISEISMO: A Multimodal Seismic Dataset and Model for Cross-Modal Seismic Understanding
May 25, 2026Sai Munikoti, Ian Stewart, Chengping Chai +4Full Waveform Inversion Multimodal Dataset
Experiments in Agentic AI for Science
May 25, 2026Judy Fox, Geoffrey FoxScientific Workflows Scientific Discovery
DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
May 25, 2026Matt L. Wiemann, Lindsay M. Smith, Peter Melchior +4Scientific Discovery Physics-Aware Models
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
May 25, 2026Shuai Wang, Xinyuan Tian, Pangpang Liu +1Autoresearch Scientific Discovery
LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation
May 25, 2026Jiabei Xiao, Yizhou Wang, Chen Tang +3Artificial Intelligence Scientists Citations
Re-defining Humor Data Objects for AI Humor Research
May 24, 2026Anna Arnett, Bang Nguyen, Meng JiangHumor Artificial Intelligence Research
Catalyst Papers in Artificial Intelligence Research: A Landscape on ICLR from 2017 to 2025
May 24, 2026Fan HuangArtificial Intelligence Research Peer Review
GRAIL: AI translation for scientists application workflow on satellite data
May 23, 2026Zhuocheng Shang, Ahmed EldawyMachine Translation Scientific Agents
The Perception-Physics Paradox: Probing Scientific Alignment with TC-Bench
May 23, 2026Dingling Yao, Andrea Polesello, Adeel Pervez +2Scientific Discovery Perceptual Understanding
Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference Components
May 23, 2026Ling Zhan, Xiaoyao Yu, Tao JiaScientific Workflows Scientific Discovery
How Much Structure Do LLMs Need? Evaluating LLMs for Bibliometric Cluster Description
May 23, 2026Abraham Camelo-Guerrero, Jairo Diaz-RodriguezReal Datacite Dois Scientific Discovery
Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment
May 22, 2026Binglu Wang, Weixin Liang, Jiahui Xue +4Scientific Discovery Multi-Model Study
AI Security Research Should Better Incentivize Defense Research
May 22, 2026Youqian ZhangArtificial Intelligence Safety Artificial Intelligence Research
GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
May 22, 2026Vartan Shadarevian, Kia Ghods, Alex Kenich +1Imperfect-Information Games Scientific Discovery
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
May 22, 2026Guiyao Tie, Jiawen Shi, Dingjie Song +20Autoresearch Artificial Intelligence Research
LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
May 21, 2026Sanchit Kabra, Nikhil Abhyankar, Saaketh Desai +2Scientific Discovery Drug Discovery

May 31, 2026 · cs.AIJ/K move · Enter open · S save

The Case for Model Science: Verify, Explore, Steer, Refine

Przemyslaw Biecek, Luca Longo, Jianlong Zhou, Thomas Fel+2

Center for Credible AI · University of Warsaw · Warsaw University of Technology · University College Cork · University of Technology Sydney

We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline, a direction we term Model Science. Complex AI models now serve billions of users, yet our understanding of how they work lags far behind our ability to deploy them. Decades of benchmark-driven research have delivered remarkable progress: extensive leaderboards, a wide range of performance metrics, tracking capability gains across diverse tasks; yet this success has also revealed the limits of benchmarks as they tell us whether models perform but not why they succeed or fail, they miss critical failure modes, such as hallucinations or shortcuts. Precedents from established sciences point the way forward: cognitive science shows that understanding complex systems requires complementary levels of analysis; neuroscience demonstrates that deep study of single cases reveals what population studies miss; medicine teaches that specialised training must develop alongside research practice; and agriculture models how shared infrastructure and principles enable cumulative progress. These lessons inform three foundations for Model Science. First, we propose to consolidate research around four functional perspectives: Verify, Explore, Steer, and Refine that address complementary questions about model behaviour. Second, we discuss the required infrastructure for cumulative knowledge: catalogues of datasets, models and findings. Third, we highlight the need for deep analysis of individual model instances, not just model families, because single cases can reveal what population studies miss.

Artificial Intelligence Models Scientific Discovery Cognitive Science Verifier Refinement Steering

Open paper Ask about it PDF