Author

Kayvan Karim

h-index 2 View on Semantic Scholar

We have 1 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Aug 2026

LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games

A runtime strategy-selection framework in which a large language model (LLM) guides a trained RL policy without modifying its underlying behavior is investigated, demonstrating both the potential and limitations of LLM-guided runtime strategy selection for adaptive multi-agent game AI.

H. D. Nair, Kayvan Karim · 0 citations