Grounding LLMs in Scientific Discovery via Embodied Actions

• URL: http://arxiv.org/abs/2602.20639v1
• Date: Tue, 24 Feb 2026 07:37:18 GMT
• Title: Grounding LLMs in Scientific Discovery via Embodied Actions
• Authors: Bo Zhang, Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Minlie Huang, Hongning Wang,
• Abstract summary: Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and physical simulation.<n>We propose EmbodiedAct, a framework that transforms established scientific software into active embodied agents by groundings in embodied actions with a tight perception-execution loop.
• Score: 84.11877211907647
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery [64.67498968405327]
  SpatialDreamer is a reinforcement learning framework that enables spatial reasoning through a closedloop process of active exploration.<n>GeoPO introduces tree-structured sampling and step-level reward estimation with consistency geometric constraints.
  arXiv  Detail & Related papers  (2025-12-08T17:20:50Z)
• SIMPACT: Simulation-Enabled Action Planning using Vision-Language Models [60.80050275581661]
  Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities.<n>They lack a grounded understanding of physical dynamics.<n>We present S, a test-time, SIMulation-enabled ACTion Planning framework.<n>Our method demonstrates state-of-the-art performance on five challenging, real-world rigid-body and deformable manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-05T18:51:03Z)
• Leveraging LLM-based agents for social science research: insights from citation network simulations [132.4334196445918]
  We introduce the CiteAgent framework, designed to generate citation networks based on human-behavior simulation.<n>CiteAgent captures predominant phenomena in real-world citation networks, including power-law distribution, citational distortion, and shrinking diameter.<n>We establish two LLM-based research paradigms in social science, allowing us to validate and challenge existing theories.
  arXiv  Detail & Related papers  (2025-11-05T08:47:04Z)
• NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents [65.85967483058705]
  Large language models are emerging as powerful tools for scientific law discovery.<n>Existing benchmarks for this task suffer from a fundamental methodological trilemma.<n>We introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains.
  arXiv  Detail & Related papers  (2025-10-08T16:12:11Z)
• LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models [35.01842161084472]
  We propose a new physical reasoning task and a dataset, dubbed TraySim.<n>Our task involves predicting the dynamics of several objects on a tray that is given an external impact.<n>We present LLMPhy, a zero-shot black-box optimization framework that leverages the physics knowledge and program synthesis abilities of LLMs.<n>Our results show that the combination of the LLM and the physics engine leads to state-of-the-art zero-shot physical reasoning performance.
  arXiv  Detail & Related papers  (2024-11-12T18:56:58Z)
• Reliable edge machine learning hardware for scientific applications [34.87898436984149]
  Extreme data rate scientific experiments create massive amounts of data that require efficient ML edge processing. We discuss approaches to developing and validating reliable algorithms at the scientific edge under such strict latency, resource, power, and area requirements.
  arXiv  Detail & Related papers  (2024-06-27T20:45:08Z)
• LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery [141.39722070734737]
  We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework. We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
  arXiv  Detail & Related papers  (2024-05-16T03:04:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.