一作ACL 2026Findings· Findings of ACL
ABC -Bench: Benchmarking Agentic Backend Coding in Real-World Development
Jie Yang · Honglin Guo · Li Ji · Jiazheng Zhou · Rui Zheng · Zhikai Lei · Shuo Zhang · Zhiheng Xi · Shichun Liu · Yuxin Wang · Bo Wang · Yining Zheng · Tao Gui · Xipeng Qiu
摘要
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks predominantly evaluate code logic in static contexts, neglecting...