OpenAGI: When LLM Meets Domain Experts
Yingqiang Ge, Wenyue Hua, Kai Mei, Jianchao Ji, Juntao Tan + 3 more
TLDR
OpenAGI is an open-source platform that integrates large language models with domain expert models to solve complex, multi-step tasks and iteratively improve through reinforcement learning.
Key contributions
- Introduces OpenAGI, a platform combining LLMs with expert models, tools, and APIs for real-world multi-step task solving.
- Implements a dual strategy using both benchmark and open-ended tasks to evaluate and expand problem-solving capabilities.
- Proposes Reinforcement Learning from Task Feedback (RLTF) to create a self-improving AI feedback loop enhancing task performance.
Why it matters
This paper matters because it presents a practical framework that mimics human intelligence by combining general reasoning (via LLMs) with specialized domain expertise, addressing a key challenge in advancing towards Artificial General Intelligence. By open-sourcing the platform and tools, it fosters collaborative research and accelerates progress in building AI systems capable of handling complex, real-world problems through continuous learning and integration of diverse expert knowledge.
Original Abstract
Human Intelligence (HI) excels at combining basic skills to solve complex tasks. This capability is vital for Artificial Intelligence (AI) and should be embedded in comprehensive AI Agents, enabling them to harness expert models for complex task-solving towards Artificial General Intelligence (AGI). Large Language Models (LLMs) show promising learning and reasoning abilities, and can effectively use external models, tools, plugins, or APIs to tackle complex problems. In this work, we introduce OpenAGI, an open-source AGI research and development platform designed for solving multi-step, real-world tasks. Specifically, OpenAGI uses a dual strategy, integrating standard benchmark tasks for benchmarking and evaluation, and open-ended tasks including more expandable models, tools, plugins, or APIs for creative problem-solving. Tasks are presented as natural language queries to the LLM, which then selects and executes appropriate models. We also propose a Reinforcement Learning from Task Feedback (RLTF) mechanism that uses task results to improve the LLM's task-solving ability, which creates a self-improving AI feedback loop. While we acknowledge that AGI is a broad and multifaceted research challenge with no singularly defined solution path, the integration of LLMs with domain-specific expert models, inspired by mirroring the blend of general and specialized intelligence in humans, offers a promising approach towards AGI. We are open-sourcing the OpenAGI project's code, dataset, benchmarks, evaluation methods, and the UI demo to foster community involvement in AGI advancement: https://github.com/agiresearch/OpenAGI.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.