Saved in:
Bibliographic Details
Main Authors: Ding, Kun, Xu, Jian, Wang, Ying, Yang, Peipei, Xiang, Shiming
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.18985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911461368922112
author Ding, Kun
Xu, Jian
Wang, Ying
Yang, Peipei
Xiang, Shiming
author_facet Ding, Kun
Xu, Jian
Wang, Ying
Yang, Peipei
Xiang, Shiming
contents Infrared radiation computing underpins advances in climate science, remote sensing and spectroscopy but remains constrained by manual workflows. We introduce InfEngine, an autonomous intelligent computational engine designed to drive a paradigm shift from human-led orchestration to collaborative automation. It integrates four specialized agents through two core innovations: self-verification, enabled by joint solver-evaluator debugging, improves functional correctness and scientific plausibility; self-optimization, realized via evolutionary algorithms with self-discovered fitness functions, facilitates autonomous performance optimization. Evaluated on InfBench with 200 infrared-specific tasks and powered by InfTools with 270 curated tools, InfEngine achieves a 92.7% pass rate and delivers workflows 21x faster than manual expert effort. More fundamentally, it illustrates how researchers can transition from manual coding to collaborating with self-verifying, self-optimizing computational partners. By generating reusable, verified and optimized code, InfEngine transforms computational workflows into persistent scientific assets, accelerating the cycle of scientific discovery. Code: https://github.com/kding1225/infengine
format Preprint
id arxiv_https___arxiv_org_abs_2602_18985
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing
Ding, Kun
Xu, Jian
Wang, Ying
Yang, Peipei
Xiang, Shiming
Artificial Intelligence
Infrared radiation computing underpins advances in climate science, remote sensing and spectroscopy but remains constrained by manual workflows. We introduce InfEngine, an autonomous intelligent computational engine designed to drive a paradigm shift from human-led orchestration to collaborative automation. It integrates four specialized agents through two core innovations: self-verification, enabled by joint solver-evaluator debugging, improves functional correctness and scientific plausibility; self-optimization, realized via evolutionary algorithms with self-discovered fitness functions, facilitates autonomous performance optimization. Evaluated on InfBench with 200 infrared-specific tasks and powered by InfTools with 270 curated tools, InfEngine achieves a 92.7% pass rate and delivers workflows 21x faster than manual expert effort. More fundamentally, it illustrates how researchers can transition from manual coding to collaborating with self-verifying, self-optimizing computational partners. By generating reusable, verified and optimized code, InfEngine transforms computational workflows into persistent scientific assets, accelerating the cycle of scientific discovery. Code: https://github.com/kding1225/infengine
title InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing
topic Artificial Intelligence
url https://arxiv.org/abs/2602.18985