Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing

Kun Ding, Jian Xu, Ying Wang, Peipei Yang, Shiming Xiang

TL;DR

This work introduces InfEngine, an autonomous intelligent computational engine designed to drive a paradigm shift from human-led orchestration to collaborative automation, and illustrates how researchers can transition from manual coding to collaborating with self-verifying, self-optimizing computational partners.

Abstract

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

InfEngine: A Self-Verifying and Self-Optimizing Intelligent Engine for Infrared Radiation Computing

TL;DR

This work introduces InfEngine, an autonomous intelligent computational engine designed to drive a paradigm shift from human-led orchestration to collaborative automation, and illustrates how researchers can transition from manual coding to collaborating with self-verifying, self-optimizing computational partners.

Abstract

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
Paper Structure (30 sections, 38 equations, 7 figures)

This paper contains 30 sections, 38 equations, 7 figures.

Table of Contents

  1. Introduction
  2. Results
  3. Experimental Setup
  4. Performance on InfBench
  5. Comparison with Different Methods
  6. Comparison with Different LLMs
  7. Comparison with Human
  8. Effectiveness of Components
  9. Case Analysis
  10. Case 1: High-Throughput Screening of Infrared Photodetector Materials
  11. Case 2: Autonomous Cross-Validation of Computational Infrared Spectroscopy Methods
  12. Case 3: Autonomous Optimization of Molecular Structure Elucidation from Infrared Spectra
  13. Case 4: Evolutionary Optimization of Image Translation Pipeline
  14. Discussion
  15. Method
  16. ...and 15 more sections

Figures (7)

  • Figure 1: Overview. a, Related applications. b, Workflow of infrared radiation computing with core computational components at each stage. c, Scientific computing based on manual coding. d, Scientific computing based on intelligent computing engine. e, The flowchart of InfEngine. f, The InfTools has 270 tools for infrared radiation computing. g, Standardized fields defined for each tool. h, Some of the general tools that can be used in InfEngine. Icon credit: https://www.freepik.com/.
  • Figure 2: Comparison with baselines. a, Performance on assistant-type tasks (left), optimization-type tasks (mid), overall performance (right). b, Win rate comparison of InfEngine and MapCoder on assistant-type tasks. c, Train Score scatter plot of InfEngine and MapCoder on optimization-type tasks, Test Score scatter plot of them on optimization-type tasks, correlation analysis between training and test scores of InfEngine, correlation analysis between training and test scores of MapCoder. d, Win rate comparison of InfEngine and InfEngine-evo on assistant-type tasks. e, Per-task Train Score comparison of InfEngine, InfEngine-evo and InfEngine-eval-evo. f, Win rate comparison of InfEngine-evo and InfEngine-eval-evo on assistant-type tasks. g, Per-task Test Score comparison of InfEngine, InfEngine-evo and InfEngine-eval-evo.
  • Figure 3: Comparison of InfEngine with different LLMs and human baseline. a, Performance on assistant-type tasks. b, Performance on optimization-type tasks. c, Aggregate performance across all tasks. d, Computational time comparison for assistant-type (left) and optimization-type (right) tasks. e, Win/Tie/Loss rate of different LLM-based InfEngine instances against the human baseline on the training set (left) and test set (right) for optimization-type tasks.
  • Figure 4: Question and result of Case 1. a, The query question with an illustration explaining the task. b, The result of Problem Analyzing Agent. c, The planning generated by Problem Solving Agent. d, The solution code and the corresponding flowchart. e, Evaluation function generated by Evaluator Generation Agent. Credit: agent icon, https://www.freepik.com/.
  • Figure 5: Question and result of Case 2. a, The query question requesting comparison of IR spectra from MD simulation and 3D structure-based prediction for ethanol (CCO). b, The result of Problem Analyzing Agent. c, The planning generated by Problem Solving Agent. d, The automated tool-chain and code execution flowchart of final solution code. e, The generated comparative visualization of normalized IR spectra by the solution code.
  • ...and 2 more figures