arXiv:2607. 24882v1 Announce Type: cross Abstract: Modern coding agents are usually evaluated by whether they eventually produce a correct patch, but patch generation depends on an earlier context-acquisition stage: finding the repository files needed for the task.
arXiv:2608. 05886v1 Announce Type: cross Abstract: Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it.
arXiv:2609. 31176v1 Announce Type: new Abstract: Repository-level issue localization aims to identify and rank the files and functions relevant to resolving a reported issue.
arXiv:2609.01601v1 Announce Type: cross Abstract: The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repo...
SkillFlow is an open, multi-stage retrieval system that helps AI agents selectively load relevant skills from a large library of community-contributed SKILL.md definitions. The pipeline uses dense retrieval, two rounds of cross-encoder reranking, and LLM-based selection to balance recall and precision. Evaluations on SkillsBench and Terminal-Bench show that SkillFlow improves performance when high-quality skills are available, but retrieval alone does not help if the corpus lacks executable skills for the target domain.
arXiv:2606. 28365v1 Announce Type: cross Abstract: RAG ingestion pipelines frequently augment search corpus index with semantic enrichment indices (e.
arXiv:2603. 26667v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) turns external documents into evidence for large language models.
arXiv:2607. 01916v1 Announce Type: new Abstract: Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where useful evidence is mixed with irrelevant code and logs.
Modern LLM coding agents such as Claude Code and OpenHands share a common inefficiency: they spend much of their token budget finding the file to patch, rather than patching it. On SWE-Bench Verified, a 30B OpenHands agent averages 23 rounds and 631K tokens per resolved issue, with many calls spent on grep, glob, and view_file during repository exploration.
Q2D-Web is a new large‑scale benchmark for agentic Retrieval‑Augmented Generation (RAG) systems, featuring a 190 million‑document web corpus and 70 k machine‑reformulated search queries in ten languages. It supplies three sets of relevance judgments—agent citations, production rankings, and a combined set enriched with LLM‑based labels—to evaluate first‑stage retrievers. Experiments on 13 retrievers show consistent ranking across judgment sets but significant variation across domains, languages, and query types, and demonstrate that a carefully sampled sub‑corpus can approximate full‑corpus evaluation with minimal loss in Recall@1000.
arXiv:2607. 09691v1 Announce Type: cross Abstract: A modern coding agent can hold an entire repository in its context window.
arXiv:2606. 08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is not selected, compressed, or surfaced at action time.
ExecRetrieval is a new benchmark for code‑embedding retrieval that contains 939 Python tasks, each with a verified correct implementation and up to four single‑edit buggy distractors generated mechanically. The dataset allows direct testing of a retriever’s ability to functionally discriminate correct code from near‑clone incorrect code, rather than relying on lexical similarity. Experiments on 23 dense embeddings and BM25 show that while the best system can retrieve the correct code within the top 10 results, it often fails to rank the correct implementation first, with rank‑1 errors dominated by paired buggy variants.