This work asks what a CAE simulation agent still needs beyond a generic harness, and finds that with information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems.
Abstract
Computer-aided engineering (CAE) simulation is among the largest and most demanding areas of engineering, where setting up a solver such as OpenFOAM, FEniCS, or COMSOL takes real expertise. Large language model (LLM) agents promise to turn a natural-language request into a working simulation, and recent CAE agents add simulation-specific machinery: multi-agent decomposition, domain retrieval, and scripted reflection. That machinery suited weak base models; modern harnesses already supply multi-turn reasoning, tool use, and execution feedback. We ask what a CAE simulation agent still needs beyond a generic harness. With information access and repair budget held fixed, a single-agent harness matches or beats multi-agent specialized systems (FoamBench 96.4\% vs.\ 88.2\%). Ablations trace this to capabilities the harness already provides: execution-feedback repair lifts FoamBench from 71.8\% with no repair round to 96.4\%, while scripted reflection adds nothing. The one input that still helps is domain knowledge supplied as solver tutorials, our largest measured gain (80.9\% to 96.4\%).
This work studies a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management, and finds that context management becomes increasingly valuable as the context-window budget tightens.
Run-Ze Fan, Zihao Zhang, Si-Min Ma et al.· 14 citations· ⚡2
Agent Gym is introduced, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop and introduces the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency.
Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge et al.· 0 citations
Experiments on guideline-following and artifact-generation tasks show that specifications can serve not merely as behavioral guidance, but as authority over compliant execution and completion.
A systematic empirical study of harness effects in SE agents shows that harness effectiveness depends jointly on model capability and task type, and highlights harness design as a first-class factor in SE-agent performance and provides insights for building more effective and efficient coding agents.
Hai-Chuan Hu, Quan-Jun Zhang, Sheng-Cheng Yu et al.· 4 citations
Scientific Agent Skills, an open library of 163 such procedures in 16 areas of practice, including genomics, cheminformatics, medical imaging, study design and scientific communication, is presented.
T. Kassis, Vinayak Agarwal, Yu-Huan He et al.· 4 citations· ⚡1
This work deploys AutoMOOSE as a agentic software, complementing the prior work which focused on development of the agentic tool, and describes its software framework and architecture through Use Case and logical views of the 1+5 architectural-views model.
Sukriti Manna, Henry Chan, Subramanian K. R. S. Sankaranarayanan· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.