11 papers
BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services
Yuzhe Guo, Mengzhou Wu, Yuan Cao +4
The paper presents BackendForge, a benchmark that evaluates how well agentic large language models can generate complete, deployable backend services from OpenAPI specifications, u…
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
Chiwang Luk, Matin Mohammad Najafi, Zhifeng Jia +6
Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where usefu…
Understanding Automated Web GUI Testing: An Empirical Study Across Exploration Strategies and State Abstractions
Chenxu Liu, Wei Yang, Ying Zhang +1
Automated web GUI testing (AWGT) relies on exploration strategies that exercise web applications through GUI actions to maximize code coverage, spanning traditional model-based, re…
An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse
Yuan Cao, Dezhi Ran, Yuzhe Guo +5
Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we o…
GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training
Yuan Cao, Dezhi Ran, Mengzhou Wu +9
Post-training GUI agents in interactive environments is critical for developing generalization and long-horizon planning capabilities. However, training on real-world applications…
Synthesizing File-Level Data for Unit Test Generation with Chain-of-Thoughts via Self-Debugging
Ziyue Hua, Tianyu Chen, Yeyun Gong +8
Automatic unit test (UT) generation is essential for software quality assurance, but existing approaches--including symbolic execution, search-based approaches, and recent LLM-base…