Papers

Filtered to AI-powered development tools · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents

73 upvotes · 28 JUL 2026 · Zhongming Yu, Hengjia Yu, Boqin Yuan et al.

This paper develops a system called CodeNib that helps coding agents navigate and retain context in evolving repositories, allowing them to work more efficiently. Practitioners in the field of artificial intelligence, software development, and human-computer interaction may care about this research because it can improve the performance and productivity of coding agents.

code completionlexical viewsrepository managementcontextual searchAI-powered development tools