Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
cs.AI, cs.SE
Submitted: 2026-06-01
Updated: 2026-08-26
Comments: Submitted to the proceedings of the deRSE26 conference
Code: https://github.com/algorithmicsuperintelligence/openevolve
Project page: https://rohaquinlop.github.io/complexipy
License: http://creativecommons.org/licenses/by/4.0/
The gist: We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve.
Terminology
Abstract
We consider LLM-based algorithm development through a case study on contractionorder optimisation for tensor networks with OpenEvolve. We pay particular attention to the choice of the LLM as well as design choices such as evaluation metric and test instances. Our results highlight both the promise of verifier-guided evolutionary coding agents for algorithm development/improvement and the continuing importance of evaluation, validation, and interpretation -- and corresponding challenges -- by the human scientist.
Sources
- Code Compass: A Study on the Challenges of Navigating Unfamiliar Codebases
- CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
- FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
- GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
- Tensor Networks in a Nutshell
- Intentmaking and Sensemaking: Human Interaction with AI-Guided Mathematical Discovery
- Even with AI, Bijection Discovery is Still Hard: The Opportunities and Challenges of OpenEvolve for Novel Bijection Construction
- New Bounds for Zarankiewicz Numbers via Reinforced LLM Evolutionary Search
- From Prompts to Power: Measuring the Energy Footprint of LLM Inference
- Let the Barbarians In: How AI Can Accelerate Systems Performance Research
- Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision
- LLM-Guided Evolutionary Search for Algebraic T-Count Optimization
- The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
- MappingEvolve: LLM-Driven Code Evolution for Technology Mapping
- Mathematical exploration and discovery at scale
- Accelerating scientific discovery with Co-Scientist
- ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
- Constructing Optimal Contraction Trees for Tensor Network Quantum Circuit Simulation
- Domain-Aware Tensor Network Structure Search
- GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection