Skip to content

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

Aug 2026 · 0 citations · 46 references
Computer Science

TL;DR

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.

Abstract

Scripted and rule-based non-player characters (NPCs) in combat video games often exhibit predictable behaviors that experienced players can exploit, while reinforcement learning (RL) agents typically retain a fixed policy after training and cannot readily adapt their strategy to different opponents. We investigate a runtime strategy-selection framework in which a large language model (LLM) guides a trained RL policy without modifying its underlying behavior. To demonstrate this, we train five NPC agents with a shared PPO policy in Unity and compare a baseline configuration, in which the policy acts independently, with an LLM-augmented configuration in which a locally hosted Mistral 7B model, accessed through Ollama, reads the live game state every five seconds and assigns one of four tactical tags. We evaluate both configurations against three scripted opponent types across 600 episodes and analyze outcomes using the Mann-Whitney U test. Against a Balanced opponent that changes tactics during an episode, the LLM-augmented agents more than doubled their win rate from 11% to 24% and produced significantly longer episodes. Against an Evasive opponent, the augmented agents achieved a higher win rate and faster kills, although their shorter episode duration did not satisfy the strict hypothesis definition. Against an Aggressive opponent, the LLM's near-constant preference for encirclement was counterproductive. Analysis of 2,430 strategy selections showed that Surround was selected in 83.8% of cases regardless of opponent type, indicating limited zero-shot strategic differentiation at this model scale. These results demonstrate both the potential and limitations of LLM-guided runtime strategy selection for adaptive multi-agent game AI.

View source

Similar papers

Preprint Aug 2026

IB-RL: Isolated Bilateral Reinforcement Learning for Strategic Dialogue Agents

Isolated Bilateral Reinforcement Learning (IB-RL), in which the two roles coevolve through joint rollouts while each role optimizes its own reward through fully independent advantages, action masks, and update paths, produces policies that generalize more effectively to unseen counterparts.

Senhao Wang, Chenghao Cai, Hai-Tao Hu et al. · 0 citations

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

UnifiedPlayers, a cooperative framework comprising a Planning Player that generates tasks, an Execution Player that produces multi-turn trajectories with Python tool calls, and an Evaluation Player that constructs executable verifiers, highlights cooperation among specialized players as a promising path toward self-enh...

Wen-Jie Liao, Liang Zhao, Ze-Hong Cao · 0 citations
Open access Aug 2026

Gaming with AI: A Hybrid Reinforcement Learning, Large Language Model, and Procedural Content Generation Framework for Enhancing Player Engagement and User Experience

This paper presents and evaluates a Hybrid AI Gaming Framework that runs three complementary modules asynchronously: a Proximal Policy Optimisation (PPO) reinforcement-learning agent for real-time difficulty calibration, a vector-grounded Memory Repository that anchors LLM-based NPC dialogue to the game's canonical wor...

Abhinav, Amandeep, Dharmender Kumar, Suraj, Keshav · 0 citations
Book Open access Aug 2026

Large Language Model (LLM) as an Excellent Reinforcement Learning Researcher in both Single-Agent and Multi-Agent Scenarios

A Self-Evolutional single-agent/multi-agent Reinforcement Learning (SE-RL) framework that utilizes a Large Language Model (LLM) to design various RL algorithm modules, such as agent model design, reward function, profiling, communication, and state imagination, by leveraging the LLM generating module output or code.

Vincent Fu, Xin-Xin Xu, Weichen Xu et al. · 0 citations
#machine learning Preprint Sep 2026

PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games

Through PlayTrain, an RL framework that combines the abilities of large language models to robustly generate JavaScript games from a minimal human prompt, and an efficient pipeline that can run any JS game in a standard'gym'environment, this work reimagine RL VGE development.

R. Truong, Lance Ying, Samuel Gershman et al. · 0 citations

Related blog posts

MIT News · Artificial Intelligence Nov 17, 2026

Learning the language of machine learning

By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.