作者位次 #9/14ACL 2026Findings· Findings of ACL
O mni C ode: A Benchmark for Evaluating Software Development Agents
Atharv Sonwane · Eng-Shen Tu · Wei-Chung Lu · Claas Beger · Carter Larsen · Debjit Dhar · Simon Alford · Rachel Chen · Ronit Pattanayak · Tuan Anh Dang · Guohao Chen · Gloria Geng · Kevin Ellis · Saikat Dutta
摘要
LLM-powered coding agents are redefining how real-world software is developed. To drive the research towards better coding agents, we require challenging benchmarks that can rigorously evaluate the ability of such agents to perform various software engineering tasks. However, popular coding bench...