Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qian, Cheng, Liang, Shihao, Qin, Yujia, Ye, Yining, Cong, Xin, Lin, Yankai, Wu, Yesai, Liu, Zhiyuan, Sun, Maosong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909082806386688
author Qian, Cheng
Liang, Shihao
Qin, Yujia
Ye, Yining
Cong, Xin
Lin, Yankai
Wu, Yesai
Liu, Zhiyuan
Sun, Maosong
author_facet Qian, Cheng
Liang, Shihao
Qin, Yujia
Ye, Yining
Cong, Xin
Lin, Yankai
Wu, Yesai
Liu, Zhiyuan
Sun, Maosong
contents This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution. Unlike existing methods focused on intra-task learning, ICE promotes the transfer of knowledge between tasks for genuine self-evolution, similar to human experience learning. The strategy dynamically investigates planning and execution trajectories, consolidates them into simplified workflows and pipelines, and exploits them for improved task execution. Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80% and significantly decreasing the demand for the model's capability. Specifically, when combined with GPT-3.5, ICE's performance matches that of raw GPT-4 across various agent tasks. We argue that this self-evolution approach represents a paradigm shift in agent design, contributing to a more robust AI community and ecosystem, and moving a step closer to full autonomy.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13996
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
Qian, Cheng
Liang, Shihao
Qin, Yujia
Ye, Yining
Cong, Xin
Lin, Yankai
Wu, Yesai
Liu, Zhiyuan
Sun, Maosong
Computation and Language
Artificial Intelligence
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution. Unlike existing methods focused on intra-task learning, ICE promotes the transfer of knowledge between tasks for genuine self-evolution, similar to human experience learning. The strategy dynamically investigates planning and execution trajectories, consolidates them into simplified workflows and pipelines, and exploits them for improved task execution. Our experiments on the XAgent framework demonstrate ICE's effectiveness, reducing API calls by as much as 80% and significantly decreasing the demand for the model's capability. Specifically, when combined with GPT-3.5, ICE's performance matches that of raw GPT-4 across various agent tasks. We argue that this self-evolution approach represents a paradigm shift in agent design, contributing to a more robust AI community and ecosystem, and moving a step closer to full autonomy.
title Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2401.13996