Problem
Research questions and friction points this paper is trying to address.
CAE simulation
LLM agents
domain knowledge
execution feedback
harness
What Do CAE Simulation Agents Really Need Beyond a Generic Harness?
๐ค AI Summary
็ ็ฉถๆข่ฎจไบCAEๆจกๆไปฃ็ๅจ้็จๆกๆถไนๅค็้ๆฑ๏ผๅ็ฐๆง่กๅ้ฆๅ้ขๅ็ฅ่ฏๆฏๆๅๆง่ฝ็ๅ
ณ้ฎๅ ็ด ใ
๐ 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\%).
Innovation
Methods, ideas, or system contributions that make the work stand out.
execution-feedback repair
domain knowledge
solver tutorials
๐ Similar Papers
No similar papers found.
