Edge 414: Inside Meta AI's HUSKY: A New Agent Optimized for Multi-Step Reasoning
New research from Meta AI, Allen AI, and the University of Washington tackles one of the most important problems in LLM reasoning.
Reasoning is highly acknowledged as the next frontier in generative AI. By reasoning, we refer to the ability to decompose a task into smaller subsets and solve those individually. Chain-of-Thought, Tree-of-Tought, Skeleton-of-Thought, and Reflexion are some of the recent techniques that have tackled reasoning capabilities in LLMs. Reasoning also involves peripherical capabilities such as accessing external data or tools. In the last couple of years, we have seen models to perform extremely well in specific reasoning techniques, but they failed to generalize across domains. This is not a surprise if we consider that reasoning is a very computationally expensive task. This is precisely the challenge that researchers from Meta AI, Allen Institute of AI and the University of Washington address in a recent paper.
HUSKY is an open-source language agent designed to handle a variety of complex tasks involving numerical, tabular, and knowledge-based reasoning. Unlike other agents that focus on specific tasks or use proprietary models, HUSKY operates within a unified framework to manage diverse challenges. It works in two stages: first, it generates the next action needed to solve a task; second, it executes this action using expert models, updating the solution as it progresses.