SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories

TL;DR

SUPER is a benchmark designed to evaluate how well large language models can autonomously set up and execute research tasks from repositories, highlighting current limitations and guiding future improvements.

Contribution

This paper introduces SUPER, the first benchmark for assessing LLMs' ability to reproduce research results from repositories, including diverse problem sets and evaluation metrics.

Findings

GPT-4o solves only 16.3% of end-to-end problems

State-of-the-art models struggle with research repository tasks

SUPER provides a challenging resource for future progress

Abstract

Given that Large Language Models (LLMs) have made significant progress in writing code, can they now be used to autonomously reproduce results from research repositories? Such a capability would be a boon to the research community, helping researchers validate, understand, and extend prior work. To advance towards this goal, we introduce SUPER, the first benchmark designed to evaluate the capability of LLMs in setting up and executing tasks from research repositories. SUPERaims to capture the realistic challenges faced by researchers working with Machine Learning (ML) and Natural Language Processing (NLP) research repositories. Our benchmark comprises three distinct problem sets: 45 end-to-end problems with annotated expert solutions, 152 sub problems derived from the expert set that focus on specific challenges (e.g., configuring a trainer), and 602 automatically generated problems for larger-scale development. We introduce various evaluation measures to assess both task success and progress, utilizing gold solutions when available or approximations otherwise. We show that state-of-the-art approaches struggle to solve these problems with the best model (GPT-4o) solving only 16.3% of the end-to-end set, and 46.1% of the scenarios. This illustrates the challenge of this task, and suggests that SUPER can serve as a valuable resource for the community to make and measure progress.