Papers by Weixi Tong
CodeJudge: Evaluating Code Generation with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown promising performance in code generation, but how to reliably evaluate code generated by LLMs remains a challenging problem. |
| Approach: | They propose a framework that leverages Large Language Models to evaluate the semantic correctness of generated code without the need for test cases. |
| Outcome: | The proposed framework outperforms existing methods on four code generation datasets and five programming languages. |
Mango: Multi-Agent Web Navigation via Global-View Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing web agents typically begin exploration from the root URL, which is inefficient for complex websites with deep hierarchical structures. |
| Approach: | They propose a multi-agent web navigation method that leverages the website structure to dynamically determine optimal starting points. |
| Outcome: | The proposed method achieves 63.6% success rate on WebVoyager, outperforming the best baseline by 7.3%, and 52.5% success rate with open-source and closed-source models. |