The field of large language models (LLMs) is rapidly advancing, with significant developments in optimization and autonomous systems. Recent research has demonstrated the effectiveness of LLMs in navigating complex parameter spaces, enabling more efficient optimization in chemistry and other fields. Additionally, LLMs are being integrated with other AI approaches, such as reinforcement learning and evolutionary computation, to create more powerful and adaptive systems. Notable papers in this area include those that propose novel frameworks for automated QUBO transformation, self-organized hierarchical variable agents, and LLM-assisted iterative evolution. These advancements have the potential to transform various fields, from chemistry and materials science to robotics and supply chain management. Noteworthy papers include LLM-QUBO, which automates the formulation-to-solution pipeline for quantum annealing, and ChemBOMAS, which accelerates Bayesian optimization in chemistry using LLM-enhanced multi-agent systems. Overall, the field is moving towards more integrated and autonomous systems, with LLMs playing a key role in driving innovation and progress.
Advancements in Large Language Models for Optimization and Autonomous Systems
Sources
Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers
LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptions
HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
A Hybrid Ai Framework For Strategic Patent Portfolio Pruning: Integrating Learning To-Rank And Market Need Analysis For Technology Transfer Optimization
ShortageSim: Simulating Drug Shortages under Information Asymmetry
Hybrid Autonomy Framework for a Future Mars Science Helicopter
Re-evaluating LLM-based Heuristic Search: A Case Study on the 3D Packing Problem
Coral: A Unifying Abstraction Layer for Composable Robotics Software
Exploring the interplay between Planetary Boundaries and Sustainable Development Goals using Large Language Models
Self-Organizing Aerial Swarm Robotics for Resilient Load Transportation : A Table-Mechanics-Inspired Approach
Leveraging LLM-Based Agents for Intelligent Supply Chain Planning
INGRID: Intelligent Generative Robotic Design Using Large Language Models
Expedition & Expansion: Leveraging Semantic Representations for Goal-Directed Exploration in Continuous Cellular Automata
AutoPBO: LLM-powered Optimization for Local Search PBO Solvers
A 13/6-Approximation for Strip Packing via the Bottom-Left Algorithm
Shared Autonomy through LLMs and Reinforcement Learning for Applications to Ship Hull Inspections
Human-LLM Synergy in Context-Aware Adaptive Architecture for Scalable Drone Swarm Operation
A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving
Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution
ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System