Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue

Mahammad Nuriyev
11/3/2025
cs.CL

Official code: MahammadNuriyev62/CPDC-challenge-2025-solution (0 stars, last commit 2025-12-23).

Abstract

We present a multi-expert system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution in interactive environments. Using Qwen3 as the base model and Low-Rank Adaptation (LoRA) adapters, we instantiate three specialists: tool calling, tool-response interpretation, and direct dialogue. Our system comfortably meets the computational efficiency requirements, delivering fast responses and maintaining modest resource usage on L40S GPUs. In the Commonsense Persona-Grounded Dialogue Challenge 2025, our method ranked second overall. Code available at: https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution/

View on arXivView PDF

Code Implementations(1)

MahammadNuriyev62/CPDC-challenge-2025-solutionOfficial100%

NPC AI agent capable of tool-calling and producing natural conversations.

00Shell, PythonAug 15, 202510 months ago
agentnpcqwentool-calling

Similar Papers

Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

84% match2025

MCPDial: A Minecraft Persona-driven Dialogue Dataset

79% match1 repo42024

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting

79% match1 repo92025

User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale

78% match2026

Dialogue Language Model with Large-Scale Persona Data Engineering

78% match2024

A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation

78% match2024

Cite this paper

@article{nuriyev2025efficient,
  title  = {Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue},
  author = {Mahammad Nuriyev},
  year   = {2025},
  eprint = {2511.01720},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.01720v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.01720.svg)](https://codeofpaper.com/paper/2511.01720)

Discussion