AgentKit: Structured LLM Reasoning with Dynamic Graphs

Yue Wu, Yewen Fan, So Yeon Min, Shrimai Prabhumoye, Stephen Marcus McAleer, Ruslan Salakhutdinov, Yonatan Bisk, Yuanzhi Li, Tom Mitchell

Research Area: Alignment, LMs for everyone, LMs and the world, LMs and embodiment, LMs and interactions

Keywords: LLM Agents

TL;DR: An intuitive LLM prompting framework for multifunctional agents, by explicitly constructing a complex "thought process" from simple natural language prompts.

Abstract:

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, in order to build a "thought process" for any problem, 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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 78