aiqbench analysis
Evolutionary Ensemble Search (EES) introduces a novel architecture for constructing machine learning procedures via expert-guided program evolution, combining code mutation with structured pipeline edits. The system utilizes a role-specialized council to direct search efforts and maintains persistent memory across runs to leverage problem-indexed lessons from previous attempts. This approach demonstrates significant performance on a cross-modal benchmark by treating development as a cumulative, executable process rather than relying solely on blind autonomous agents.
Evolutionary Ensemble Search: Council-Guided Program Evolution with Persistent Memory
arXiv:2609.17590v1 Announce Type: cross Abstract: Evolutionary Ensemble Search (EES) constructs machine-learning procedures through expert-guided program evolution. A role-specialized council turns task evidence and experimental results into structured search directions. An orchestrator allocates these directions to execution specialists and an evolutionary engine. The engine selects measured parents, diagnoses their errors, and produces descendants through code mutation, structured pipeline edits, and crossover. Each child must execute and acquire its own validation evidence. Population archives retain useful alternatives, while compatible predictions compete in a validation-gated ensemble stage. Search adapts through parent-relative operator credit, session memory, and problem-indexed lessons retrieved across runs. We specify these mechanisms, distinguish their execution profiles, and define the contracts required to compare candidates as their computations change. A public MLE-bench Lite development ledger records medal-threshold artifacts on 19 of 22 tasks (86.36\%), with best outcomes of 11 gold, five silver, and three bronze. The procedures span text, images, tables, audio, scientific geometry, and deterministic transformations. The campaign includes grade feedback between runs, external-source routes, and mixed confirmation procedures; its aggregate is an achieved development result, not a blind autonomous-agent success rate. The report contributes a concrete architecture for cumulative executable search and a versioned account of its cross-modal development outcomes.
Abstract:Evolutionary Ensemble Search (EES) constructs machine-learning procedures through expert-guided program evolution. A role-specialized council turns task evidence and experimental results into structured search directions. An orchestrator allocates these directions to execution specialists and an evolutionary engine. The engine selects measured parents, diagnoses their errors, and produces descendants through code mutation, structured pipeline edits, and crossover. Each child must execute and acquire its own validation evidence. Population archives retain useful alternatives, while compatible predictions compete in a validation-gated ensemble stage. Search adapts through parent-relative operator credit, session memory, and problem-indexed lessons retrieved across runs. We specify these mechanisms, distinguish their execution profiles, and define the contracts required to compare candidates as their computations change. A public MLE-bench Lite development ledger records medal-threshold artifacts on 19 of 22 tasks (86.36\%), with best outcomes of 11 gold, five silver, and three bronze. The procedures span text, images, tables, audio, scientific geometry, and deterministic transformations. The campaign includes grade feedback between runs, external-source routes, and mixed confirmation procedures; its aggregate is an achieved development result, not a blind autonomous-agent success rate. The report contributes a concrete architecture for cumulative executable search and a versioned account of its cross-modal development outcomes.
Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI)
arXiv:2609.17590 [cs.NE]
(or arXiv:2609.17590v1 [cs.NE] for this version)
https://doi.org/10.48550/arXiv.2609.17590 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 293 words
Related coverage
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
arXiv · Aug 25, 2026
Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
arXiv · Oct 16, 2026
MEMENTO: Memory-Guided Memetic Code-as-Policy Evolution
arXiv · Jul 28, 2026
Self-Improving Language Models with Bidirectional Evolutionary Search
arXiv · Oct 14, 2026