TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON

TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token usage), TaskGen uses StrictJSON that ensures JSON...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Chong Min Tan, John, Prince, Saroj, Runwal, Bharat, Maheshwari, Hardik, Brian Lim Yi Sheng, Cottrill, Richard, Chona, Alankrit, Kumar, Ambuj, Motani, Mehul
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 22.07.2024
Subjects
Datasets
Error correction
Information management
Large language models
Obstacle avoidance
Reagents
Online AccessGet full text

Cover

More Information
Summary:TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token usage), TaskGen uses StrictJSON that ensures JSON output from the Large Language Model (LLM), along with additional features such as type checking and iterative error correction. Key to the philosophy of TaskGen is the management of information/memory on a need-to-know basis. We empirically evaluate TaskGen on various environments such as 40x40 dynamic maze navigation with changing obstacle locations (100% solve rate), TextWorld escape room solving with dense rewards and detailed goals (96% solve rate), web browsing (69% of actions successful), solving the MATH dataset (71% solve rate over 100 Level-5 problems), Retrieval Augmented Generation on NaturalQuestions dataset (F1 score of 47.03%)
ISSN:2331-8422