Manish Sanwal

Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models

2025 · arXiv (Cornell University)

Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can produce misleading explanations. In …