ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

TL;DR

ScienceAgentBench is a comprehensive benchmark designed to rigorously evaluate the capabilities of language agents in data-driven scientific discovery, revealing current limitations and guiding future improvements.

Contribution

The paper introduces ScienceAgentBench, a validated, multi-disciplinary benchmark with 102 tasks, evaluation metrics, and strategies to assess and improve scientific language agents.

Findings

Best agents solve only ~32% of tasks independently

Performance improves to 42% with increased compute and cost

Current language agents have significant limitations in scientific code generation

Abstract

The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true capabilities. In this work, we call for rigorous assessment of agents on individual tasks in a scientific workflow before making bold claims on end-to-end automation. To this end, we present ScienceAgentBench, a new benchmark for evaluating language agents for data-driven scientific discovery. To ensure the scientific authenticity and real-world relevance of our benchmark, we extract 102 tasks from 44 peer-reviewed publications in four disciplines and engage nine subject matter experts to validate them. We unify the target output for every task to a self-contained Python program file and employ an array of evaluation metrics to examine the generated programs, execution results, and costs. Each task goes through multiple rounds of manual validation by annotators and subject matter experts to ensure its annotation quality and scientific plausibility. We also propose two effective strategies to mitigate data contamination concerns. Using ScienceAgentBench, we evaluate five open-weight and proprietary LLMs, each with three frameworks: direct prompting, OpenHands CodeAct, and self-debug. Given three attempts for each task, the best-performing agent can only solve 32.4% of the tasks independently and 34.3% with expert-provided knowledge. In addition, we evaluate OpenAI o1-preview with direct prompting and self-debug, which can boost the performance to 42.2%, demonstrating the effectiveness of increasing inference-time compute but with more than 10 times the cost of other LLMs. Still, our results underscore the limitations of current language agents in generating code for data-driven discovery, let alone end-to-end automation for scientific research.