Paper
Grounding LLMs in Scientific Discovery via Embodied Actions
Authors
Bo Zhang, Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Minlie Huang, Hongning Wang
Abstract
Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and verifiable physical simulation. Existing solutions operate in a passive "execute-then-response" loop and thus lacks runtime perception, obscuring agents to transient anomalies (e.g., numerical instability or diverging oscillations). To address this limitation, we propose EmbodiedAct, a framework that transforms established scientific software into active embodied agents by grounding LLMs in embodied actions with a tight perception-execution loop. We instantiate EmbodiedAct within MATLAB and evaluate it on complex engineering design and scientific modeling tasks. Extensive experiments show that EmbodiedAct significantly outperforms existing baselines, achieving SOTA performance by ensuring satisfactory reliability and stability in long-horizon simulations and enhanced accuracy in scientific modeling.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2602.20639v1</id>\n <title>Grounding LLMs in Scientific Discovery via Embodied Actions</title>\n <updated>2026-02-24T07:37:18Z</updated>\n <link href='https://arxiv.org/abs/2602.20639v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2602.20639v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and verifiable physical simulation. Existing solutions operate in a passive \"execute-then-response\" loop and thus lacks runtime perception, obscuring agents to transient anomalies (e.g., numerical instability or diverging oscillations). To address this limitation, we propose EmbodiedAct, a framework that transforms established scientific software into active embodied agents by grounding LLMs in embodied actions with a tight perception-execution loop. We instantiate EmbodiedAct within MATLAB and evaluate it on complex engineering design and scientific modeling tasks. Extensive experiments show that EmbodiedAct significantly outperforms existing baselines, achieving SOTA performance by ensuring satisfactory reliability and stability in long-horizon simulations and enhanced accuracy in scientific modeling.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <published>2026-02-24T07:37:18Z</published>\n <arxiv:comment>24 pages, 7 figures, 7 tables. Preprint</arxiv:comment>\n <arxiv:primary_category term='cs.AI'/>\n <author>\n <name>Bo Zhang</name>\n </author>\n <author>\n <name>Jinfeng Zhou</name>\n </author>\n <author>\n <name>Yuxuan Chen</name>\n </author>\n <author>\n <name>Jianing Yin</name>\n </author>\n <author>\n <name>Minlie Huang</name>\n </author>\n <author>\n <name>Hongning Wang</name>\n </author>\n </entry>"
}