9 papers
Is Your Benchmark Still Useful? Dynamic Benchmarking for Code Language Models
Batu Guan, Xiao Wu, Yuanyuan Yuan +1
In this paper, we tackle a critical challenge in model evaluation: how to keep code benchmarks useful when models might have already seen them during training. We introduce a novel…
Understanding Agent-Based Patching of Compiler Missed Optimizations
Batu Guan, Zirui Wang, Shaohua Li
Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to implement or patch such missed optimi…
Archer: Towards Agentic Review for Compiler Optimizations
Yunbo Ni, Shaohua Li
Modern compilers are frequently updated, but expert review capacity is highly limited, leading to delayed integration and, in some cases, subtle semantic bugs entering the compiler…
Knowdit: Agentic Smart Contract Vulnerability Detection with Auditing Knowledge Summarization
Ziqiao Kong, Wanxu Xia, Chong Wang +6
Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulnerabilities are tightly coupl…
Agentic Harness for Real-World Compilers
Yingwei Zheng, Cong Li, Shaohua Li +2
Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable automated bug repair, compiler bugs p…
Belobog: Move Language Fuzzing Framework For Real-World Smart Contracts
Ziqiao Kong, Wanxu Xia, Zhengwei Li +6
Move is a resource-oriented programming language designed for secure and verifiable smart contract development and has been widely used in managing billions of digital assets in bl…