Evolution without an Oracle: Driving Effective Evolution with LLM Judges

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zhe, Yang, Yuheng, Wen, Haibin, Qiu, Xiaojie, Zhang, Zaixi, Zhang, Qingfu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917101969604608
author Zhao, Zhe
Yang, Yuheng
Wen, Haibin
Qiu, Xiaojie
Zhang, Zaixi
Zhang, Qingfu
author_facet Zhao, Zhe
Yang, Yuheng
Wen, Haibin
Qiu, Xiaojie
Zhang, Zaixi
Zhang, Qingfu
contents The integration of Large Language Models (LLMs) with Evolutionary Computation (EC) has unlocked new frontiers in scientific discovery but remains shackled by a fundamental constraint: the reliance on an Oracle--an objective, machine-computable fitness function. This paper breaks this barrier by asking: Can evolution thrive in a purely subjective landscape governed solely by LLM judges? We introduce MADE (Multi-Agent Decomposed Evolution), a framework that tames the inherent noise of subjective evaluation through "Problem Specification." By decomposing vague instructions into specific, verifiable sub-requirements, MADE transforms high-variance LLM feedback into stable, precise selection pressure. The results are transformative: across complex benchmarks like DevAI and InfoBench, MADE outperforms strong baselines by over 50% in software requirement satisfaction (39.9% to 61.9%) and achieves a 95% perfect pass rate on complex instruction following. This work validates a fundamental paradigm shift: moving from optimizing "computable metrics" to "describable qualities," thereby unlocking evolutionary optimization for the vast open-ended domains where no ground truth exists.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19489
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evolution without an Oracle: Driving Effective Evolution with LLM Judges
Zhao, Zhe
Yang, Yuheng
Wen, Haibin
Qiu, Xiaojie
Zhang, Zaixi
Zhang, Qingfu
Software Engineering
Artificial Intelligence
The integration of Large Language Models (LLMs) with Evolutionary Computation (EC) has unlocked new frontiers in scientific discovery but remains shackled by a fundamental constraint: the reliance on an Oracle--an objective, machine-computable fitness function. This paper breaks this barrier by asking: Can evolution thrive in a purely subjective landscape governed solely by LLM judges? We introduce MADE (Multi-Agent Decomposed Evolution), a framework that tames the inherent noise of subjective evaluation through "Problem Specification." By decomposing vague instructions into specific, verifiable sub-requirements, MADE transforms high-variance LLM feedback into stable, precise selection pressure. The results are transformative: across complex benchmarks like DevAI and InfoBench, MADE outperforms strong baselines by over 50% in software requirement satisfaction (39.9% to 61.9%) and achieves a 95% perfect pass rate on complex instruction following. This work validates a fundamental paradigm shift: moving from optimizing "computable metrics" to "describable qualities," thereby unlocking evolutionary optimization for the vast open-ended domains where no ground truth exists.
title Evolution without an Oracle: Driving Effective Evolution with LLM Judges
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.19489