PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Yajie, Feng, Yue
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915253080555520
author Yu, Yajie
Feng, Yue
author_facet Yu, Yajie
Feng, Yue
contents Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective cognition chains including reasoning, planning, decision-making and reflecting remains limited, especially in the dynamically interactive scenarios. In addition, unlike human, prompt-based responses face challenges in psychological state perception and empirical calibration during uncertain gaming process, which can inevitably lead to cognition bias. In light of above, we introduce PolicyEvol-Agent, a comprehensive LLM-empowered framework characterized by systematically acquiring intentions of others and adaptively optimizing irrational strategies for continual enhancement. Specifically, PolicyEvol-Agent first obtains reflective expertise patterns and then integrates a range of cognitive operations with Theory of Mind alongside internal and external perspectives. Simulation results, outperforming RL-based models and agent-based methods, demonstrate the superiority of PolicyEvol-Agent for final gaming victory. Moreover, the policy evolution mechanism reveals the effectiveness of dynamic guideline adjustments in both automatic and human evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind
Yu, Yajie
Feng, Yue
Artificial Intelligence
Machine Learning
Multi-agents has exhibited significant intelligence in real-word simulations with Large language models (LLMs) due to the capabilities of social cognition and knowledge retrieval. However, existing research on agents equipped with effective cognition chains including reasoning, planning, decision-making and reflecting remains limited, especially in the dynamically interactive scenarios. In addition, unlike human, prompt-based responses face challenges in psychological state perception and empirical calibration during uncertain gaming process, which can inevitably lead to cognition bias. In light of above, we introduce PolicyEvol-Agent, a comprehensive LLM-empowered framework characterized by systematically acquiring intentions of others and adaptively optimizing irrational strategies for continual enhancement. Specifically, PolicyEvol-Agent first obtains reflective expertise patterns and then integrates a range of cognitive operations with Theory of Mind alongside internal and external perspectives. Simulation results, outperforming RL-based models and agent-based methods, demonstrate the superiority of PolicyEvol-Agent for final gaming victory. Moreover, the policy evolution mechanism reveals the effectiveness of dynamic guideline adjustments in both automatic and human evaluation.
title PolicyEvol-Agent: Evolving Policy via Environment Perception and Self-Awareness with Theory of Mind
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2504.15313