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.
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. 19957v1 Announce Type: new Abstract: Natural language code retrieval is a rapidly evolving task in computer science.
arXiv:2605. 17561v2 Announce Type: replace-cross Abstract: Issues faced when using software are reported in the form of bug reports.
SpIDER is a dense retrieval method that combines LLM reasoning with graph-based exploration of codebases to locate relevant functions, classes, or files for user queries. It introduces a graph-structured benchmark, SpIDER-Bench, covering multiple programming languages and demonstrates significant recall improvements over traditional BM25 and dense approaches. The method’s graph-based candidate expansion provides auditable structural reasons for each retrieved item while keeping the retrieval budget fixed.
arXiv:2506. 11066v3 Announce Type: replace-cross Abstract: Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging.
The paper presents a controlled comparison of six retrieval-augmented generation (RAG) strategies for scientific question answering on a large arXiv corpus. All pipelines use the same LLM generator and evaluation protocol, differing only in retrieval design—ranging from classic dense retrieval to late‑interaction methods like ColBERTv2. The authors also release a synthetic question dataset and code to enable reproducible, large‑scale evaluation of RAG trade‑offs.
arXiv:2606. 30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query.
arXiv:2605. 11374v5 Announce Type: replace Abstract: Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain.
arXiv:2605. 16046v2 Announce Type: replace-cross Abstract: Semantic code search has been widely adopted in both academia and industry.
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...
arXiv:2607. 26766v1 Announce Type: cross Abstract: Code search in large-scale ecosystems is often hindered by the lexical gap between user queries and implementation details, alongside the trade-off between the low latency of traditional Information Retrieval (IR) and the precision of Deep Learning (DL).
RankEvolve is an auto‑research framework that evolves generative ranking models by orchestrating multiple large‑language‑model coding agents through an Executable Operating Protocol (EOP). The system compiles a state machine that enforces phases, gates, branches, and loops, while a meta‑meta‑harness lets agents review and repair each other’s code. In budget‑matched experiments, heterogeneous composition of agents raised execution accuracy from 45.8 % to 62.5 % and reduced silent critical‑defect rates, achieving notable gains on the HSTU recommender and other benchmarks.