AI Paper Atlas

Research map / Large language models / Agents, code and math

SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs

Yadi Cao, Sicheng Lai, Jiahe Huang, Yang Zhang, Zach Lawrence, Rohan Bhakta, Izzy F. Thomas, Mingyun Cao, Chung-Hao Tsai, Zihao Zhou, Yidong Zhao, Hao Liu and 3 more

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use multi-round instead of single-round inferenceLLMs · SimulCost (11 solvers)success rate: 45-62% -> 66-81%Improved
tighten accuracy requirement low to highLLMs single-round · SimulCostsuccess rate (%): 64 -> 39Hurt
tighten accuracy requirement low to highLLMs multi-round · SimulCostsuccess rate (%): 73 -> 71No clear effect
use multi-round instead of single-round at high accuracyLLMs · SimulCostsuccess rate: +30.5Improved
add in-context examples (ICL) (ablation)Claude-3.7-Sonnet single-round · SimulCost ablation subsetsuccess rate: +28.7Improved
add in-context examples (ICL) (ablation)Claude-3.7-Sonnet multi-round · SimulCost ablation subsetsuccess rateHurt
include cost information in ICL examples (ablation)Claude-3.7-Sonnet single-round · SimulCost ablation subsetefficiencyImproved
use LLM instead of Bayesian optimization (BO-GP)multi-round tuning · SimulCost, low accuracyefficiency: 1.05 -> 2.13Improved
increase GPT-5 reasoning effort (ablation)GPT-5 · SimulCostsuccess rateNo clear effect
let LLM provide initial guess for search algorithmsearch algorithms · SimulCostsuccess rate: +8.6Mixed
add multi-round inference for Misc parametersLLMs · SimulCost task groupssuccess rate: +28Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy