AI-Assisted Scientific Research

Follow this topic Ask about this topic

Momentum

14 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 162

All topics

Negative Knowledge as Failure-aware Shared Memory for AutoResearch
Jun 19, 2026Hanchun WangAI-Assisted Scientific Research Memory-Augmented Agents
Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.
Querying an astronomical database using large language models: the ALeRCE text-to-SQL system
Jun 16, 2026P. A. Estevez, J. Espejo-Moreira, S. Sanfeliu-Alvarez +10LLM Prompting AI-Assisted Scientific Research
Department of Electrical Engineering, University of Chile, Av. Tupper 2007, Santiago, Chile · Millennium Institute of Astrophysics (MAS), Nuncio Monseñor Sótero Sanz 100, Providencia, Santiago, Chile · Departamento de Astronomía, Universidad de Chile, Casilla 36D, Santiago, Chile +11
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
Jun 16, 2026Xinyang Liao, Lingyu Li, Huacan Liu +5AI-Assisted Scientific Research AI Agent Safety Benchmarks
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio
Jun 15, 2026Anzhe Xie, Weihang Su, Yujia Zhou +2AI-Assisted Scientific Research LLM Agent Evaluation
Tsinghua University Beijing, China
Stable Menus of Public Goods: AI-Enabled Progress
Jun 15, 2026Sara FishAI-Assisted Scientific Research Human-AI Collaboration
School of Engineering and Applied Sciences, Harvard University.
Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods
Jun 15, 2026Francesca Carlon, Brecht Verbeken, Vincent Ginis +1LLM Evaluation AI-Assisted Scientific Research
1Data Analytics Lab, Vrije Universiteit Brussel, Pleinlaan 5, 1050 Brussels, Belgium · 2imec-SMIT, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Brussels, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
Jun 15, 2026Sirui Lu, Xiao-Liang QiAI-Assisted Scientific Research Scientific Communication
1Max-Planck-Institut für Quantenoptik, Garching, Germany · 2Munich Center for Quantum Science and Technology (MCQST), Schellingstrasse 4, D-80799 München, Germany · 3Leinweber Institute for Theoretical Physics, Stanford University, Stanford, CA, USA
From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithms
Jun 12, 2026Yanqiao Wang, Jin-Peng Liu, Peng Li +1AI-Assisted Scientific Research Human-AI Co-Creation
Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Yau Mathematical Sciences Center, Tsinghua University, Beijing, China · Qiuzhen College, Tsinghua University, Beijing, China +3
AI can help scientists publish less
Jun 11, 2026Gianfranco BertoneAI-Assisted Scientific Research
Gravitation Astroparticle Physics Amsterdam (GRAPPA), University of Amsterdam, 1098 XH Amsterdam, The Netherlands
Automated reproducibility assessments in the social and behavioral sciences using large language models
Jun 11, 2026Tobias Holtdirk, Pietro Marcolongo, Anna Steinberg Schulten +7AI-Assisted Scientific Research Scientific Reproducibility
1LMU Munich, Munich, Germany · 2Munich Center for Machine Learning, Munich, Germany · University of Maryland, College Park, USA +1
CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models
Jun 11, 2026Yu Fu, Yongqi Kang, Yong ZhaoLLM Evaluation AI-Assisted Scientific Research
Sichuan University
(Human) Attention Is (Still) All You Need: Human oversight makes AI-assisted social science reliable
Jun 11, 2026Chen Zhu, Xiaolu Wang, Weilong ZhangAI Agent Reliability AI-Assisted Scientific Research
China Agricultural University · University of Cambridge
Search Discipline for Long-Horizon Research Agents
Jun 9, 2026Adithya Srinivasan, Devesh ParagiriAI-Assisted Scientific Research Long-Horizon Agent Evaluation
Department of Computer Science · North Carolina State University · University of Maryland
Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Auditable Biomedical Informatics Architecture
Jun 8, 2026Yoojin Nam, Jinhoon Jeong, Namkug KimLLM Answer Verification LLM Auditing
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea · Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea · Aperivue, Incheon, Republic of Korea +2
GIScholarBench: Benchmarking LLM Overconfidence in GIS Research
Jun 6, 2026Zongrng Li, Mingzheng Yang, Lei Zou +8LLM Evaluation AI-Assisted Scientific Research
Department of Geography Texas A&M University College Station, TX, USA · Google Mountain View, CA, USA · Department of Landscape Architecture and Urban Planning Texas A&M University College Station, TX, USA
Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model
Jun 5, 2026Karla Tame-Narvaez, Aleksandra Ćiprijanović, Shubhendu TrivediUncertainty Quantification AI-Assisted Scientific Research
Scientific Computing Division Fermi National Accelerator Laboratory Batavia, IL 60510 · Department of Astronomy and Astrophysics University of Chicago Chicago, IL 60637 · Fermi National Accelerator Laboratory Batavia, IL 60510 +1
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle
Jun 5, 2026Jiayu Wang, Weijiang Lv, Bowen Fu +8AI-Assisted Scientific Research AI Agent Evaluation
Xi’an Jiaotong University · Xidian University
MIRAI: Prediction and Generation of High-Impact Academic Research
Jun 3, 2026Alex Li, Joseph JacobsonAI-Assisted Scientific Research Research Idea Generation
MIT Media Lab Cambridge, MA
AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis
Jun 1, 2026Massimiliano Pronesti, Angelo Miculescu, Mohsin Kapdi +8AI-Assisted Scientific Research Clinical Information Extraction
1IBM Research · 2Dublin City University · University of Oxford +2
HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval
May 29, 2026Yang Yang, Boyun Xu, Hao Fu +6AI-Assisted Scientific Research Information Retrieval
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511400, China · Shandong University, Weihai Campus, 180 Wenhua West Road, Weihai, 264209, Shandong, P.R. China · Institute of Deep Perception Technology, JITRI, Wuxi 214000, China
Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration
May 27, 2026Sandra Woolley, Tim Collins, Khalid Khattak +3Healthcare Human-AI Agreement
a Keele University, UK · b Manchester Metropolitan University, UK
ResearchLoop: An Evidence-Gated Control Plane for AI-Assisted Research
May 27, 2026Yihan Xia, Taotao WangAI-Assisted Scientific Research Scientific Reproducibility
Shenzhen University, China
Computational Modeling of Antibody-Antigen Complexes: PLM-Based and MSA-Based Approaches
May 27, 2026Xiao LuoProtein Structure Prediction AI-Assisted Scientific Research
TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO, CHICAGO, ILLINOIS
Considerations for an Integrated Detector Design at FCC-ee: A Human-AI Exploration
May 25, 2026Charles YoungAI-Assisted Scientific Research High-Energy Physics
SLAC National Accelerator Laboratory
LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation
May 25, 2026Jiabei Xiao, Yizhou Wang, Chen Tang +3RL for Language Model Reasoning AI-Assisted Scientific Research
1The Chinese University of Hong Kong · 2Shanghai Artificial Intelligence Laboratory · 3Fudan University
How Much Structure Do LLMs Need? Evaluating LLMs for Bibliometric Cluster Description
May 23, 2026Abraham Camelo-Guerrero, Jairo Diaz-RodriguezLLM Evaluation Clustering
School of Information Technology York University Toronto, Ontario M3J 1P3 · Department of Mathematics and Statistics York University Toronto, Ontario M3J 1P3
Human-AI Collaboration in Science at Scale: A Global Large-scale Randomized Field Experiment
May 22, 2026Binglu Wang, Weixin Liang, Jiahui Xue +4AI-Assisted Scientific Research Human-AI Collaboration
Kellogg School of Management, Northwestern University, Evanston, IL, USA · Center for Science of Science and Innovation, Northwestern University, Evanston, IL, USA · Northwestern Institute on Complex Systems, Northwestern University, Evanston, IL, USA +3
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
May 21, 2026Yuxuan Chen, Changwei Lv, Yunduo Xiao +5AI-Assisted Scientific Research Molecular Generation
School of Electronic and Computer Engineering, Peking University, Shenzhen, China · Tsinghua University, Beijing, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China
Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference
May 21, 2026Hai-Ling Lu, Yu-Yang Li, Yin-Bi Li +4AI-Assisted Scientific Research
National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, China · University of Chinese Academy of Sciences, Beijing 100049, China · School of Astronomy and Space Science, University of Chinese Academy of Sciences, Beijing 100049, China +1
Atom-level Protein Representation Learning Improves Protein Structure Prediction
May 21, 2026Taewon Kim, Hyosoon Jang, Hyunjin Seo +6Protein Structure Prediction Self-Supervised Pre-Training
Graduate School of AI, KAIST · Department of Chemistry, KAIST · HITS Inc. +3

Jun 19, 2026, cs.AIJ/K move · Enter open · S save

Negative Knowledge as Failure-aware Shared Memory for AutoResearch

Hanchun Wang

Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.

AI-Assisted Scientific Research Memory-Augmented Agents Autonomous Research Agents

Open paper AskPDF arXiv

AI-assisted research systems generate many failed attempts, but those failures rarely become a durable, shared knowledge asset. We propose a negative knowledge memory layer: a curator agent converts each failed attempt into a bounded, typed record in a shared bank, and a downstream research agent explicitly adopts or rejects those records before proposing its next experiment. We evaluate this layer in two settings: same-task retry on ScienceAgentBench and cross-task scientific research on two nonlinear math-physics PDE problems. The negative knowledge layer outperforms vanilla AutoResearch baselines while using fewer tokens; agents with the negative knowledge bank solve new tasks that all baselines fail to solve in PDE systems research. We also show that the previous negative knowledge bank can transfer and enhance AutoResearch on different PDE problems. These results suggest that structured negative knowledge is a knowledge asset that should be explicitly maintained in broader AI-engaged scientific research beyond a memory-compression or debugging aid, alongside positive findings, as a collective infrastructure for scientific memory. Code is available at https://github.com/hch-wang/Negative_Knowledge.

Momentum

Related topics

Latest papers 162