LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
Proposes LLM-AutoSciLab, a closed-loop framework that combines hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. It iteratively proposes plausible hypotheses, selects informative experiments, and updates state based on evidence. Introduces ActiveSciBench with 57 enzyme-kinetics tasks and 45 gene-regulatory-network tasks. Achieves 67.6% symbolic accuracy on NewtonBench, 35.1% on ActiveSciBench-Chem, and 31.1% exact graph recovery on ActiveSciBench-GRN, with 2-5x sample efficiency over baselines.
Article intelligence
Key points
- LLM-AutoSciLab iteratively proposes hypotheses, selects informative experiments, and refines mechanisms in a closed loop.
- Introduces ActiveSciBench, a benchmark with enzyme-kinetics and gene-regulatory-network tasks for evaluating active scientific discovery.
- Outperforms prior methods with 2-5x sample efficiency and state-of-the-art accuracy across multiple benchmarks.
Why it matters
This matters because LLM-AutoSciLab iteratively proposes hypotheses, selects informative experiments, and refines mechanisms in a closed loop.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.24043] LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
[Submitted on 21 May 2026]
Title:LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
View a PDF of the paper titled LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs, by Sanchit Kabra and 4 other authors
View PDF HTML (experimental)
Abstract:Scientific discovery is a closed-loop process in which hypotheses guide data acquisition and observations refine the hypothesis space. Yet most approaches reduce discovery to supervised learning over fixed datasets, where limited observations can support multiple plausible mechanisms that fit locally but fail to generalize. Thus, the key challenge is selecting informative observations to resolve uncertainty, shifting the focus from static inference to adaptive data acquisition. To address this, we propose LLM-AutoSciLab, a closed-loop framework that couples hypothesis generation with hypothesis-conditioned experiment selection and mechanism refinement. Rather than fitting models to passively collected data, LLM-AutoSciLab iteratively proposes plausible hypotheses, selects informative experiments to distinguish or refine them, and updates its state using the resulting evidence. To evaluate dynamic, closed-loop scientific discovery with active data acquisition, we introduce ActiveSciBench, comprising two datasets: ActiveSciBench-Chem with 57 enzyme-kinetics tasks and ActiveSciBench-GRN with 45 gene-regulatory-network tasks. These datasets model discovery as a budget-constrained process requiring adaptive experiment design, variable selection, and recovery of true mechanisms. Across NewtonBench, ActiveSciBench-Chem, and ActiveSciBench-GRN, LLM-AutoSciLab outperforms prior methods, achieving 67.6% and 35.1% symbolic accuracy on NewtonBench and ActiveSciBench-Chem, respectively, and 31.1% exact graph recovery on ActiveSciBench-GRN. Moreover, hypothesis-guided experimentation is 2-5x more sample-efficient than the strongest competing baselines. Code and data are available at: this https URL
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2605.24043 [cs.LG]
(or arXiv:2605.24043v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.24043
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Sanchit Kabra [view email] [v1] Thu, 21 May 2026 20:30:56 UTC (2,354 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs, by Sanchit Kabra and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.LG
new | recent | 2026-05
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender (What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)