A self-correcting multi-agent LLM framework for language-based physics simulation and explanation
Year: 2026
Type: article
Abstract: Physics-based simulations are essential in science and engineering, yet creating them typically requires expert knowledge of numerical solvers and governing equations. Large language models (LLMs) offer new possibilities for natural language-based simulation, but they often fail when prompts are vague, incomplete, or multilingual. We present MCP-SIM ( M emory- C oordinated P hysics-Aware Sim ulation), a self-correcting multi-agent framework that transforms underspecified prompts into validated simulations and explanatory reports. The system integrates input clarification, code generation, error diagnosis, and multilingual explanation through structured agent collaboration and persistent memory. Rather than relying on one-shot code generation, MCP-SIM emulates expert-like reasoning via iterative plan–act–reflect–revise cycles. Tested on a twelve-task benchmark across diverse physics domains, MCP-SIM achieved 100% success, significantly outperforming baseline LLMs. In addition to numerical accuracy, the system produces interpretable, language-localized reports that explain each simulation’s physical logic. MCP-SIM represents a step toward general-purpose autonomous scientific assistants that simulate, adapt, and teach through natural language.
Source: npj Artificial Intelligence
Authors: Donggeun Park, Hyeonbin Moon, Seunghwa Ryu
Institution: Korea Advanced Institute of Science and Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,590
Award: G4235001168
OpenAlex ID: W7124960098