Saved in:
Bibliographic Details
Main Authors: Ren, Jinhui, Li, Huaiming, Liu, Yabin, Li, Tao, Liu, Zhaokun, Liang, Yujia, Ge, Zengle, Wu, Chufan, Yuan, Xiaomin, Liu, Danyu, Li, Annan, Wu, Jianmin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.21698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915883062919168
author Ren, Jinhui
Li, Huaiming
Liu, Yabin
Li, Tao
Liu, Zhaokun
Liang, Yujia
Ge, Zengle
Wu, Chufan
Yuan, Xiaomin
Liu, Danyu
Li, Annan
Wu, Jianmin
author_facet Ren, Jinhui
Li, Huaiming
Liu, Yabin
Li, Tao
Liu, Zhaokun
Liang, Yujia
Ge, Zengle
Wu, Chufan
Yuan, Xiaomin
Liu, Danyu
Li, Annan
Wu, Jianmin
contents High-fidelity vehicle drag evaluation is constrained less by solver runtime than by workflow friction: geometry cleanup, meshing retries, queue contention, and reproducibility failures across teams. We present a contract-centric blueprint for self-evolving coding agents that discover executable surrogate pipelines for predicting drag coefficient $C_d$ under industrial constraints. The method formulates surrogate discovery as constrained optimization over programs, not static model instances, and combines Famou-Agent-style evaluator feedback with population-based island evolution, structured mutations (data, model, loss, and split policies), and multi-objective selection balancing ranking quality, stability, and cost. A hard evaluation contract enforces leakage prevention, deterministic replay, multi-seed robustness, and resource budgets before any candidate is admitted. Across eight anonymized evolutionary operators, the best system reaches a Combined Score of 0.9335 with sign-accuracy 0.9180, while trajectory and ablation analyses show that adaptive sampling and island migration are primary drivers of convergence quality. The deployment model is explicitly ``screen-and-escalate'': surrogates provide high-throughput ranking for design exploration, but low-confidence or out-of-distribution cases are automatically escalated to high-fidelity CFD. The resulting contribution is an auditable, reusable workflow for accelerating aerodynamic design iteration while preserving decision-grade reliability, governance traceability, and safety boundaries.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21698
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction
Ren, Jinhui
Li, Huaiming
Liu, Yabin
Li, Tao
Liu, Zhaokun
Liang, Yujia
Ge, Zengle
Wu, Chufan
Yuan, Xiaomin
Liu, Danyu
Li, Annan
Wu, Jianmin
Artificial Intelligence
High-fidelity vehicle drag evaluation is constrained less by solver runtime than by workflow friction: geometry cleanup, meshing retries, queue contention, and reproducibility failures across teams. We present a contract-centric blueprint for self-evolving coding agents that discover executable surrogate pipelines for predicting drag coefficient $C_d$ under industrial constraints. The method formulates surrogate discovery as constrained optimization over programs, not static model instances, and combines Famou-Agent-style evaluator feedback with population-based island evolution, structured mutations (data, model, loss, and split policies), and multi-objective selection balancing ranking quality, stability, and cost. A hard evaluation contract enforces leakage prevention, deterministic replay, multi-seed robustness, and resource budgets before any candidate is admitted. Across eight anonymized evolutionary operators, the best system reaches a Combined Score of 0.9335 with sign-accuracy 0.9180, while trajectory and ablation analyses show that adaptive sampling and island migration are primary drivers of convergence quality. The deployment model is explicitly ``screen-and-escalate'': surrogates provide high-throughput ranking for design exploration, but low-confidence or out-of-distribution cases are automatically escalated to high-fidelity CFD. The resulting contribution is an auditable, reusable workflow for accelerating aerodynamic design iteration while preserving decision-grade reliability, governance traceability, and safety boundaries.
title A Blueprint for Self-Evolving Coding Agents in Vehicle Aerodynamic Drag Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2603.21698