AgentKit: Structured LLM Reasoning with Dynamic Graphs
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_ | 1866917732444798976 |
|---|---|
| author | Wu, Yue Fan, Yewen Min, So Yeon Prabhumoye, Shrimai McAleer, Stephen Bisk, Yonatan Salakhutdinov, Ruslan Li, Yuanzhi Mitchell, Tom |
| author_facet | Wu, Yue Fan, Yewen Min, So Yeon Prabhumoye, Shrimai McAleer, Stephen Bisk, Yonatan Salakhutdinov, Ruslan Li, Yuanzhi Mitchell, Tom |
| contents | We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts. The basic building block in AgentKit is a node, containing a natural language prompt for a specific subtask. The user then puts together chains of nodes, like stacking LEGO pieces. The chains of nodes can be designed to explicitly enforce a naturally structured "thought process". For example, for the task of writing a paper, one may start with the thought process of 1) identify a core message, 2) identify prior research gaps, etc. The nodes in AgentKit can be designed and combined in different ways to implement multiple advanced capabilities including on-the-fly hierarchical planning, reflection, and learning from interactions. In addition, due to the modular nature and the intuitive design to simulate explicit human thought process, a basic agent could be implemented as simple as a list of prompts for the subtasks and therefore could be designed and tuned by someone without any programming experience. Quantitatively, we show that agents designed through AgentKit achieve SOTA performance on WebShop and Crafter. These advances underscore AgentKit's potential in making LLM agents effective and accessible for a wider range of applications. https://github.com/holmeswww/AgentKit |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_11483 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AgentKit: Structured LLM Reasoning with Dynamic Graphs Wu, Yue Fan, Yewen Min, So Yeon Prabhumoye, Shrimai McAleer, Stephen Bisk, Yonatan Salakhutdinov, Ruslan Li, Yuanzhi Mitchell, Tom Artificial Intelligence Machine Learning We propose an intuitive LLM prompting framework (AgentKit) for multifunctional agents. AgentKit offers a unified framework for explicitly constructing a complex "thought process" from simple natural language prompts. The basic building block in AgentKit is a node, containing a natural language prompt for a specific subtask. The user then puts together chains of nodes, like stacking LEGO pieces. The chains of nodes can be designed to explicitly enforce a naturally structured "thought process". For example, for the task of writing a paper, one may start with the thought process of 1) identify a core message, 2) identify prior research gaps, etc. The nodes in AgentKit can be designed and combined in different ways to implement multiple advanced capabilities including on-the-fly hierarchical planning, reflection, and learning from interactions. In addition, due to the modular nature and the intuitive design to simulate explicit human thought process, a basic agent could be implemented as simple as a list of prompts for the subtasks and therefore could be designed and tuned by someone without any programming experience. Quantitatively, we show that agents designed through AgentKit achieve SOTA performance on WebShop and Crafter. These advances underscore AgentKit's potential in making LLM agents effective and accessible for a wider range of applications. https://github.com/holmeswww/AgentKit |
| title | AgentKit: Structured LLM Reasoning with Dynamic Graphs |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.11483 |