ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913767519944704 |
|---|---|
| author | Chen, Ziru Chen, Shijie Ning, Yuting Zhang, Qianheng Wang, Boshi Yu, Botao Li, Yifei Liao, Zeyi Wei, Chen Lu, Zitong Dey, Vishal Xue, Mingyi Baker, Frazier N. Burns, Benjamin Adu-Ampratwum, Daniel Huang, Xuhui Ning, Xia Gao, Song Su, Yu Sun, Huan |
| author_facet | Chen, Ziru Chen, Shijie Ning, Yuting Zhang, Qianheng Wang, Boshi Yu, Botao Li, Yifei Liao, Zeyi Wei, Chen Lu, Zitong Dey, Vishal Xue, Mingyi Baker, Frazier N. Burns, Benjamin Adu-Ampratwum, Daniel Huang, Xuhui Ning, Xia Gao, Song Su, Yu Sun, Huan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05080 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery Chen, Ziru Chen, Shijie Ning, Yuting Zhang, Qianheng Wang, Boshi Yu, Botao Li, Yifei Liao, Zeyi Wei, Chen Lu, Zitong Dey, Vishal Xue, Mingyi Baker, Frazier N. Burns, Benjamin Adu-Ampratwum, Daniel Huang, Xuhui Ning, Xia Gao, Song Su, Yu Sun, Huan Computation and Language Artificial Intelligence Machine Learning 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. |
| title | ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.05080 |