Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms

arXiv:2503.10968 · cs.AI, cs.CL, cs.LG, cs.SE · Submitted 2025-03-14 · Read on arXiv

cs.AI, cs.CL, cs.LG, cs.SE

Submitted: 2025-03-14

Updated: 2025-07-18

Journal ref: Inteligencia Artificial, 29(77), 2026

DOI: 10.4114/intartif.vol29iss77pp108-132

Code: https://github.com/Valdecy/pyCombinatorialhttps:

Project page: https://camilochs.github.io/comb-opt-for-all

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

Terminology

• Combinatorial Optimization — 30× in this paper · explained in 2 episodes
• Reinforcement Learning — 15× in this paper · explained in 4 episodes
• Travelling Salesman Problem — 12× in this paper
• Benchmark — 10× in this paper · explained in 2 episodes
• Branch and Bound — 9× in this paper
• Genetic Algorithm — 6× in this paper
• Large Language Models (LLMs) — 5× in this paper · explained in 6 episodes
• In-Context Learning — 3× in this paper · explained in 4 episodes
• Prompt Engineering — 3× in this paper · explained in 4 episodes
• Pruning — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Adaptive Large Neighborhood Search — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Simulated Annealing — 2× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Algorithmic Improvements — 1× in this paper · explained in 1 episode
• Ant Colony Optimization — 1× in this paper
• EMMA — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• An Alternative Softmax Operator for Reinforcement Learning
• Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models
• An Empirical Investigation of Correlation between Code Complexity and Bugs
• A Survey on In-context Learning
• When Large Language Model Meets Optimization
• Source-Aware Training Enables Knowledge Attribution in Language Models
• Evolution of Heuristics: Towards Efficient Automatic Algorithm Design Using Large Language Model
• Large Language Models as Evolutionary Optimizers
• At Which Training Stage Does Code Data Help LLMs Reasoning?
• GPT-4 Technical Report
• Improving Existing Optimization Algorithms with LLMs
• The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• The Llama 3 Herd of Models
• LiveBench: A Challenging, Contamination-Limited LLM Benchmark
• Large Language Models as Optimizers

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