SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery

SpecEvo: parallel Speculators, a trajectory-aware Advisor, and an adaptive Navigator.

Abstract

SpecEvo is a multi-LLM evolutionary framework for scientific discovery that explores with lightweight models and consolidates with frontier reasoning. Parallel Speculators propose programs, a trajectory-aware Advisor turns successes and failures into reusable guidance, and a frontier Navigator intervenes at sparse checkpoints, so that model coordination adapts as the search progresses rather than following fixed roles. Across 176 tasks in four domains, SpecEvo is competitive with frontier-model baselines on mathematical discovery and systems optimization at up to 80% lower API cost, achieves a 3.8% higher mean normalized score than the strongest baseline on CO-Bench combinatorial optimization, and attains the lowest NMSE in all eight LSR-Synth equation discovery settings among the main evolutionary baselines.

Publication
arXiv preprint arXiv:2610.28706
Ha Minh Hieu
Ha Minh Hieu
SRI Research Intern Alumnus (May ‘26–Aug ‘26)

Research Intern

Tongyao Zhu
Tongyao Zhu
IPP Doctoral Student (Jan ‘23; SEA)
Co-Supervised by Qian Liu.
Research Achievement Award (RAA, ‘25)

PhD Candidate January 2023 Intake

Xuan Long Do
Xuan Long Do
A*STAR Doctoral Student (Aug ‘23)
Co-Supervised by Kenji Kawaguchi and Nancy F. Chen
Research Achievement Award (RAA, ‘24); Dean’s Graduate Research Excellence Award (DGA, ‘26)

PhD Candidate August 2023 Intake

Min-Yen Kan
Min-Yen Kan
Associate Professor

WING lead; interests include Digital Libraries, Information Retrieval and Natural Language Processing.