The field of large language models (LLMs) is rapidly advancing, with a focus on applying these models to complex problem-solving tasks. Recent developments have shown that LLMs can be used to tackle tasks such as network resource allocation, constrained optimization, and multi-agent reasoning. These models have demonstrated remarkable capabilities in natural language understanding and generation, and are being explored for their potential to enhance reinforcement learning, genetic algorithms, and other areas of artificial intelligence. Notably, researchers are investigating ways to combine multiple LLMs to achieve better performance, such as through ensemble methods or coordinator models. Some notable papers in this area include: LM4Opt-RA, which introduces a multi-candidate LLM framework with structured ranking for automating network resource allocation, achieving state-of-the-art results with a LAME score of 0.8007. TRINITY, an evolved LLM coordinator that consistently outperforms individual models and existing methods across coding, math, reasoning, and domain knowledge tasks, achieving a score of 86.2% on LiveCodeBench.
Large Language Models for Complex Problem-Solving
Sources
LM4Opt-RA: A Multi-Candidate LLM Framework with Structured Ranking for Automating Network Resource Allocation
Constrained Network Slice Assignment via Large Language Models
ART: Adaptive Response Tuning Framework -- A Multi-Agent Tournament-Based Approach to LLM Response Optimization
Guided Self-Evolving LLMs with Minimal Human Supervision
Phase-Adaptive LLM Framework with Multi-Stage Validation for Construction Robot Task Allocation: A Systematic Benchmark Against Traditional Optimization Algorithms
Evaluating Hydro-Science and Engineering Knowledge of Large Language Models
Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks
MultiGA: Leveraging Multi-Source Seeding in Genetic Algorithms
Learning to Orchestrate Agents in Natural Language with the Conductor
Cross-Task Benchmarking and Evaluation of General-Purpose and Code-Specific Large Language Models
TRINITY: An Evolved LLM Coordinator