• Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] Title:Grounding LLMs in Scientific Discovery via Embodied Actions View PDF HTML (experimental)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. • References & Citations export BibTeX citation Loading…

Article Summaries:

  • Grounding LLMs in Scientific Discovery via Embodied Actions

Researchers introduce EmbodiedAct, a framework that turns conventional scientific software into active agents by tightly coupling large language models (LLMs) with real‑time perception and execution loops. Implemented in MATLAB, EmbodiedAct enables LLMs to interact continuously with simulation environments, detecting and responding to transient anomalies such as numerical instability or diverging oscillations-issues that passive “execute‑then‑response” systems miss. In complex engineering design and scientific modeling benchmarks, EmbodiedAct outperforms existing baselines, achieving state‑of‑the‑art accuracy while improving reliability and stability over long‑horizon simulations. The study demonstrates that embodied interaction can bridge the gap between theoretical reasoning and verifiable physical simulation in AI‑driven discovery.

Sources: