Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- meta-llama/Llama-3.1-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- reasoning
|
| 7 |
+
- agent
|
| 8 |
+
- program
|
| 9 |
+
- code
|
| 10 |
+
---
|
| 11 |
+
**CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis**
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Paper: https://arxiv.org/pdf/2503.23145
|
| 15 |
+
|
| 16 |
+
Code: https://github.com/Anjiang-Wei/CodeARC
|
| 17 |
+
|
| 18 |
+
Website: https://anjiang-wei.github.io/CodeARC-Website/
|
| 19 |
+
|
| 20 |
+
```
|
| 21 |
+
@article{wei2025codearc,
|
| 22 |
+
title={CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis},
|
| 23 |
+
author={Wei, Anjiang and Suresh, Tarun and Cao, Jiannan and Kannan, Naveen and Wu, Yuheng and Yan, Kai and Teixeira, Thiago SFX and Wang, Ke and Aiken, Alex},
|
| 24 |
+
journal={arXiv preprint arXiv:2503.23145},
|
| 25 |
+
year={2025}
|
| 26 |
+
}
|
| 27 |
+
```
|