Papers by Shudan Zhang

3 papers
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Copied to clipboard

Challenge: Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach: They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome: The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.
NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Queries (2024.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) generate code for productive activities, but current benchmarks for code synthesis are oriented towards introductory tasks on algorithm and data science.
Approach: They propose a code benchmark to mirror the complexity and variety of scenarios in real-world coding tasks.
Outcome: The proposed benchmark improves on 39 large language models with close HumanEval scores and achieves an efficiency increase of more than 4 times.
AndroidGen: Building an Android Language Agent under Data Scarcity (2025.acl-long)

Copied to clipboard

Challenge: Existing LLMs lack high-quality data sources and lack robust data filtration strategies.
Approach: They develop a framework to enhance the capabilities of LLM-based agents under data scarcity.
Outcome: The proposed framework improves the capabilities of LLM-based agents under data scarcity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations