Bridging Large Language Models and Optimization: A Unified Framework for Text-attributed Combinatorial Optimization

2024/08/22 by Xia Jiang, Yaoxin Wu, Jiang, Xia +5 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2408.12214

openalex publication_date 2024/08/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

To advance capabilities of large language models (LLMs) in solving combinatorial optimization problems (COPs), this paper presents the Language-based Neural COP Solver (LNCS), a novel framework that is unified for the end-to-end resolution of diverse text-attributed COPs. LNCS leverages LLMs to encode problem instances into a unified semantic space, and integrates their embeddings with a Transformer-based solution generator to produce high-quality solutions. By training the solution generator with conflict-free multi-task reinforcement learning, LNCS effectively enhances LLM performance in tackling COPs of varying types and sizes, achieving state-of-the-art results across diverse problems. Extensive experiments validate the effectiveness and generalizability of the LNCS, highlighting its potential as a unified and practical framework for real-world COP applications.

Cited by

• Large Language Models as End-to-end Combinatorial Optimization Solvers
• Large Language Models in Operations Research: Methods, Applications, and Challenges

Related

• Large Language Models as End-to-end Combinatorial Optimization Solvers
• Combinatorial Optimization for All: Using LLMs to Aid Non-Experts in Improving Optimization Algorithms
• Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach
• Can Large Language Models Be Trusted as Evolutionary Optimizers for Network-Structured Combinatorial Problems?
• CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization