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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Xia, Wu, Yaoxin, Wang, Yuan, Zhang, Yingqian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915063220142080
author Jiang, Xia
Wu, Yaoxin
Wang, Yuan
Zhang, Yingqian
author_facet Jiang, Xia
Wu, Yaoxin
Wang, Yuan
Zhang, Yingqian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12214
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging Large Language Models and Optimization: A Unified Framework for Text-attributed Combinatorial Optimization
Jiang, Xia
Wu, Yaoxin
Wang, Yuan
Zhang, Yingqian
Artificial Intelligence
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.
title Bridging Large Language Models and Optimization: A Unified Framework for Text-attributed Combinatorial Optimization
topic Artificial Intelligence
url https://arxiv.org/abs/2408.12214