# Emotional Cognitive Modeling Framework with Desire-Driven Objective Optimization for LLM-empowered Agent in Social Simulation

arXiv: https://arxiv.org/abs/2510.13195 · HTML: https://mlsanity.com/paper/2510.13195/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 10 of 10)

- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs](https://mlsanity.com/paper/2210.13312/) (2022)
- [The Next Chapter: A Study of Large Language Models in Storytelling](https://mlsanity.com/paper/2301.09790/) (2023)
- [Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench](https://mlsanity.com/paper/2308.03656/) (2023)
- [Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment](https://mlsanity.com/paper/2501.03486/) (2025)
- [Refashioning Emotion Recognition Modelling: The Advent of Generalised Large Models](https://mlsanity.com/paper/2308.11578/) (2023)
- [Automatically Select Emotion for Response via Personality-affected Emotion Transition](https://mlsanity.com/paper/2106.15846/) (2021)
- [Dynamic Game-Theoretical Decision-Making Framework for Vehicle-Pedestrian Interaction with Human Bounded Rationality](https://mlsanity.com/paper/2409.15629/) (2024)
- [Reading Users' Minds from What They Say: An Investigation into LLM-based Empathic Mental Inference](https://mlsanity.com/paper/2403.13301/) (2024)

## Abstract (arXiv)

The advent of large language models (LLMs) has enabled agents to represent virtual humans in societal simulations, facilitating diverse interactions within complex social systems. However, existing LLM-based agents exhibit severe limitations in affective cognition: They fail to simulate the bounded rationality essential for bridging virtual and real-world services; They lack empirically validated integration mechanisms embedding emotions within agent decision architectures. This paper constructs an emotional cognition framework incorporating desire generation and objective management, designed to achieve emotion alignment between LLM-based agents and humans, modeling the complete decision-making process of LLM-based agents, encompassing state evolution, desire generation, objective optimization, decision generation, and action execution. This study implements the proposed framework within our proprietary multi-agent interaction environment. Experimental results demonstrate that agents governed by our framework not only exhibit behaviors congruent with their emotional states but also, in comparative assessments against other agent types, demonstrate superior ecological validity and generate decision outcomes that significantly more closely approximate human behavioral patterns.