Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution

arXiv:2608.05651 · cs.CL, cs.AI, cs.NE · Submitted 2026-08-06 · Read on arXiv

Sichun Luo, Yi Huang, Guanzhi Deng, Haibo Wang, Haochen Luo, Lei Li, Zefa Hu, Junlan Feng, Qi Liu

cs.CL, cs.AI, cs.NE

Submitted: 2026-08-06

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 10× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Training-Free Framework — 4× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
• New Bounds for Zarankiewicz Numbers via Reinforced LLM Evolutionary Search
• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• EvoX: Meta-Evolution for Automated Discovery
• Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
• SeaEvo: Advancing Algorithm Discovery with Strategy Space Evolution
• Illuminating search spaces by mapping elites
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
• LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search
• PACEvolve: Enabling Progress-Aware Consistent Evolution

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering