Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.03101 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910190718156800 |
|---|---|
| author | Liu, Hao Yang, Xiao-Wen Sehgal, Atharva Wang, Yixin Guo, Lan-Zhe Li, Yu-Feng Yue, Yisong |
| author_facet | Liu, Hao Yang, Xiao-Wen Sehgal, Atharva Wang, Yixin Guo, Lan-Zhe Li, Yu-Feng Yue, Yisong |
| contents | Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional approaches, primarily based on genetic algorithms and related evolutionary methods, have proven useful but suffer from scalability and expressivity limitations. Recently, large language model (LLM)-based evolutionary search methods have been introduced into SR and show promise. However, existing LLM-based approaches typically rely on scalar evaluation metrics, such as mean squared error, as the sole source of feedback during the search process, thereby overlooking the rich information embedded in the dataset. To address this limitation, we propose a novel LLM-based evolutionary search framework that incorporates programmatic context augmentation. By enabling code-based interactions with the dataset, our method can actively perform data analysis and extract informative signals, beyond aggregated evaluation scores. We evaluate our framework on advanced benchmarks, such as LLM-SRBench, and demonstrate superior efficiency and accuracy compared to strong baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03101 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Programmatic Context Augmentation for LLM-based Symbolic Regression Liu, Hao Yang, Xiao-Wen Sehgal, Atharva Wang, Yixin Guo, Lan-Zhe Li, Yu-Feng Yue, Yisong Artificial Intelligence Symbolic regression (SR), the task of discovering mathematical expressions that best describe a given dataset, remains a fundamental challenge in scientific discovery. Traditional approaches, primarily based on genetic algorithms and related evolutionary methods, have proven useful but suffer from scalability and expressivity limitations. Recently, large language model (LLM)-based evolutionary search methods have been introduced into SR and show promise. However, existing LLM-based approaches typically rely on scalar evaluation metrics, such as mean squared error, as the sole source of feedback during the search process, thereby overlooking the rich information embedded in the dataset. To address this limitation, we propose a novel LLM-based evolutionary search framework that incorporates programmatic context augmentation. By enabling code-based interactions with the dataset, our method can actively perform data analysis and extract informative signals, beyond aggregated evaluation scores. We evaluate our framework on advanced benchmarks, such as LLM-SRBench, and demonstrate superior efficiency and accuracy compared to strong baselines. |
| title | Programmatic Context Augmentation for LLM-based Symbolic Regression |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.03101 |