LLM-based coding agents have shown strong performance on automated issue resolution benchmarks, yet existing evaluations largely focus on final task success, providing limited insight into how agents retrieve and use code context during problem solving. We introduce ContextBench, a process-oriented evaluation of context retrieval in coding agents. ContextBench consists of 1,136 issue-resolution tasks from 66 repositories across eight programming languages, each augmented with human-annotated gold contexts. We further implement an automated evaluation framework that tracks agent trajectories and measures context recall, precision, and efficiency throughout issue resolution. Using ContextBench, we evaluate four frontier LLMs and five coding agents. Our results show that sophisticated agent scaffolding yields only marginal gains in context retrieval ("The Bitter Lesson" of coding agents), LLMs consistently favor recall over precision, and substantial gaps exist between explored and utilized context. ContextBench augments existing end-to-end benchmarks with intermediate gold-context metrics that unbox the issue-resolution process. These contexts offer valuable intermediate signals for guiding LLM reasoning in software tasks.
Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Tasks
State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学，中国）；National Institute of Healthcare Data Science, Nanjing University, China（健康数据科学国家研究院，南京大学，中国）
An Agentic AI System for Multi-Framework Communication Coding
Duke School of Medicine（杜克大学医学院）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；MedStar Health National Center for Human Factors in Healthcare（MedStar Health国家医疗人因中心）；University of Pennsylvania（宾夕法尼亚大学）；Duke Cancer Institute（杜克癌症研究所）；Duke University（杜克大学）
