Large language models discover complementary heuristics for combinatorial optimization
Summary
A Nature Machine Intelligence paper showing that large language models can discover complementary heuristics for combinatorial optimization problems, improving solution quality by combining LLM-generated strategies.
View Cached Full Text
Cached at: 10/12/26, 07:06 AM
Similar Articles
Generating Robust Portfolios of Optimization Models using Large Language Models
Proposes a method to generate portfolios of optimization models using LLMs, with theoretical guarantees and empirical validation.
Large Language Models as Optimizers: A Survey of Direct vs. Tool-Augmented Approaches and Their Performance Frontiers
This survey categorizes LLM-based optimization into three paradigms—direct, tool-augmented, and tool-creating—and reviews their performance frontiers and limitations.
Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions
The paper introduces SDDL, a neuro-symbolic framework that improves combinatorial optimization accuracy in resource-constrained language models by translating natural-language problems into formal representations, resulting in higher feasibility rates compared to direct-generation and solver-code baselines.
HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization
This paper introduces HMACE, a heterogeneous multi-agent collaborative evolution framework that uses Large Language Models to automate heuristic design for NP-hard combinatorial optimization problems. It demonstrates improved quality-efficiency trade-offs over single-agent and multi-agent baselines on problems like TSP and BPP.
Discovering Reinforcement Learning Interfaces with Large Language Models
This paper introduces LIMEN, an LLM-guided evolutionary framework that automatically discovers reinforcement learning interfaces by jointly optimizing observation mappings and reward functions from raw simulator states. The approach reduces manual engineering effort and demonstrates that co-designing observations and rewards outperforms optimizing either component alone.