The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
arXiv:2611.07286v1 Announce Type: cross Abstract: LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still access repositories through raw files, l...
arXiv:2609.37143v1 Announce Type: cross Abstract: Modern coding agents can deliver increasingly large repository-level changes, and recent benchmarks reflect this by emphasizing long-horizon tasks wi...
Modern coding agents can deliver increasingly large repository-level changes, and recent benchmarks reflect this by emphasizing long-horizon tasks with large reference implementations. Many benchmarks...
arXiv:2606. 11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue.
Chronos is a test‑time framework that transforms historical pull requests into structured experience cards linked by a typed graph of code, developer intent, and organizational relations. It uses semantic search and weighted multi‑hop expansion to retrieve relevant cards, guiding both patch generation and selection by LLM‑based code agents. The approach improves resolution rates across multiple LLM backbones on SWE‑Bench and related benchmarks, and human evaluation shows a higher number of useful cards retrieved compared to flat semantic retrieval.
Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step.