THREAD: Thinking Deeper with Recursive Spawning
Philip Schroeder, Nathaniel Morgan, Hongyin Luo, James Glass

TL;DR
The paper introduces THREAD, a recursive threading framework for large language models that dynamically spawns sub-threads to improve reasoning and task decomposition, achieving state-of-the-art results on multiple benchmarks.
Contribution
We propose THREAD, a novel recursive threading approach enabling LLMs to dynamically decompose tasks, significantly enhancing performance across diverse benchmarks.
Findings
THREAD achieves state-of-the-art results with GPT-4 and GPT-3.5.
THREAD outperforms existing frameworks by 10-50% with smaller models.
Dynamic threading improves task decomposition and reasoning capabilities.
Abstract
Large language models (LLMs) have shown impressive capabilities across diverse settings, but still struggle as the length and complexity of the context increases. To address this challenge, we propose Thinking Recursively and Dynamically (ThReaD). THREAD frames model generation as a thread of execution that, based on the context, can run to completion or dynamically spawn new threads. By spawning, threads can offload work (e.g., thinking, retrieving information) to child threads, which only return tokens needed for the parent thread to do its work. In effect, this enables the model to adapt, as needed, the amount of intermediate work used to produce tokens. We apply THREAD in the settings of LLM task solving and question answering, where the dynamic threading allows the model to recursively decompose the given task or question into progressively simpler sub-problems that can be solved…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Multimodal Machine Learning Applications · Artificial Intelligence in Healthcare and Education
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · 15 Ways to Contact How can i speak to someone at Delta Airlines · Attention Is All You Need · Label Smoothing · Adam · Position-Wise Feed-Forward Layer · Dropout · Dense Connections · Absolute Position Encodings · Softmax
