Collaborative Evolving Strategy for Automatic Data-Centric Development
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913447192559616 |
|---|---|
| author | Yang, Xu Chen, Haotian Feng, Wenjun Wang, Haoxue Ye, Zeqi Shen, Xinjie Yang, Xiao Sun, Shizhao Liu, Weiqing Bian, Jiang |
| author_facet | Yang, Xu Chen, Haotian Feng, Wenjun Wang, Haoxue Ye, Zeqi Shen, Xinjie Yang, Xiao Sun, Shizhao Liu, Weiqing Bian, Jiang |
| contents | Artificial Intelligence (AI) significantly influences many fields, largely thanks to the vast amounts of high-quality data for machine learning models. The emphasis is now on a data-centric AI strategy, prioritizing data development over model design progress. Automating this process is crucial. In this paper, we serve as the first work to introduce the automatic data-centric development (AD^2) task and outline its core challenges, which require domain-experts-like task scheduling and implementation capability, largely unexplored by previous work.
By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges. Specifically, our proposed Co-STEER agent enriches its domain knowledge through our proposed evolving strategy and develops both its scheduling and implementation skills by accumulating and retrieving domain-specific practical experience. With an improved schedule, the capability for implementation accelerates. Simultaneously, as implementation feedback becomes more thorough, the scheduling accuracy increases. These two capabilities evolve together through practical feedback, enabling a collaborative evolution process.
Extensive experimental results demonstrate that our Co-STEER agent breaks new ground in AD^2 research, possesses strong evolvable schedule and implementation ability, and demonstrates the significant effectiveness of its components. Our Co-STEER paves the way for AD^2 advancements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18690 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Collaborative Evolving Strategy for Automatic Data-Centric Development Yang, Xu Chen, Haotian Feng, Wenjun Wang, Haoxue Ye, Zeqi Shen, Xinjie Yang, Xiao Sun, Shizhao Liu, Weiqing Bian, Jiang Artificial Intelligence Artificial Intelligence (AI) significantly influences many fields, largely thanks to the vast amounts of high-quality data for machine learning models. The emphasis is now on a data-centric AI strategy, prioritizing data development over model design progress. Automating this process is crucial. In this paper, we serve as the first work to introduce the automatic data-centric development (AD^2) task and outline its core challenges, which require domain-experts-like task scheduling and implementation capability, largely unexplored by previous work. By leveraging the strong complex problem-solving capabilities of large language models (LLMs), we propose an LLM-based autonomous agent, equipped with a strategy named Collaborative Knowledge-STudying-Enhanced Evolution by Retrieval (Co-STEER), to simultaneously address all the challenges. Specifically, our proposed Co-STEER agent enriches its domain knowledge through our proposed evolving strategy and develops both its scheduling and implementation skills by accumulating and retrieving domain-specific practical experience. With an improved schedule, the capability for implementation accelerates. Simultaneously, as implementation feedback becomes more thorough, the scheduling accuracy increases. These two capabilities evolve together through practical feedback, enabling a collaborative evolution process. Extensive experimental results demonstrate that our Co-STEER agent breaks new ground in AD^2 research, possesses strong evolvable schedule and implementation ability, and demonstrates the significant effectiveness of its components. Our Co-STEER paves the way for AD^2 advancements. |
| title | Collaborative Evolving Strategy for Automatic Data-Centric Development |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.18690 |