Supplement Generation Training for Enhancing Agentic Task Performance

TL;DR

The paper proposes Supplement Generation Training (SGT), a method where smaller models generate supplemental text to improve large model performance on agentic tasks, reducing costs and increasing flexibility.

Contribution

SGT introduces a scalable, efficient approach for enhancing large language models with dynamically generated supplements without retraining the entire model.

Findings

SGT improves task performance by providing relevant supplemental information.

The approach reduces computational costs compared to training large models for each task.

SGT enables more flexible deployment of LLMs in real-world scenarios.

Abstract

Training large foundation models for agentic tasks is increasingly impractical due to the high computational costs, long iteration cycles, and rapid obsolescence as new models are continuously released. Instead of post-training massive models for every new task or domain, we propose Supplement Generation Training (SGT), a more efficient and sustainable strategy. SGT trains a smaller LLM to generate useful supplemental text that, when appended to the original input, helps the larger LLM solve the task more effectively. These lightweight models can dynamically adapt supplements to task requirements, improving performance without modifying the underlying large models. This approach decouples task-specific optimization from large foundation models and enables more flexible, cost-effective deployment of LLM-powered agents in real-world applications.