Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social Networks

Ann Nedime Nese Rende, Tolga Yilmaz, Özgür Ulusoy
7/13/2025
cs.SIcs.MA

No official code found. Best implementation: bilkent-sna/negotiating-comfort-with-llm-agents (2 stars, MIT, last commit 2025-07-16).

Abstract

We use generative agents powered by large language models (LLMs) to simulate a social network in a shared residential building, driving the temperature decisions for a central heating system. Agents, divided into Family Members and Representatives, consider personal preferences, personal traits, connections, and weather conditions. Daily simulations involve family-level consensus followed by building-wide decisions among representatives. We tested three personality traits distributions (positive, mixed, and negative) and found that positive traits correlate with higher happiness and stronger friendships. Temperature preferences, assertiveness, and selflessness have a significant impact on happiness and decisions. This work demonstrates how LLM-driven agents can help simulate nuanced human behavior where complex real-life human simulations are difficult to set.

View on arXivView PDF

Code Implementations(1)

bilkent-sna/negotiating-comfort-with-llm-agentsCommunity66%
MIT

Code for the paper: Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social Networks

20Jupyter NotebookJul 15, 20251 years agoMIT

Similar Papers

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

88% match2025

Learning to Make Friends: Coaching LLM Agents toward Emergent Social Ties

86% match2025

Generative Agents: Interactive Simulacra of Human Behavior

86% match4 repos21.7k2023

Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions

86% match2025

LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities

86% match2024

The Power of Personality: A Human Simulation Perspective to Investigate Large Language Model Agents

85% match2025

Cite this paper

@article{rende2025negotiating,
  title  = {Negotiating Comfort: Simulating Personality-Driven LLM Agents in Shared Residential Social Networks},
  author = {Ann Nedime Nese Rende and Tolga Yilmaz and Özgür Ulusoy},
  year   = {2025},
  eprint = {2507.09657},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.09657v1}
}

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/2507.09657.svg)](https://codeofpaper.com/paper/2507.09657)

Discussion