TaskGen: A Task-Based, Memory-Infused Agentic Framework using StrictJSON
It addresses the problem of inefficient and verbose task-solving in AI agents for developers, though it is incremental as it builds on existing agent and memory management concepts.
TaskGen is an agentic framework that tackles arbitrary tasks by breaking them into subtasks, using StrictJSON to reduce token usage and ensure structured outputs, achieving high solve rates like 100% on dynamic maze navigation and 96% on escape room tasks.
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%)