LLM agents are increasingly used for repository-level software engineering tasks. However, most agents still access repositories through raw files, lexical search, and shell commands, treating code pr...
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...
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.
arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete r...
arXiv:2610.34633v1 Announce Type: cross Abstract: Repository-level code migration rewrites an entire project in a new programming language while preserving its observable behavior. It is challenging...
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.
The paper analyzes 2,487 tasks from five public coding‑agent benchmarks and 14,922 runs of six agent configurations, introducing the Spread‑Novelty‑Centrality (SNC) profile to describe how reference solutions are distributed, added, and the code’s dependencies, history, and complexity. It finds that every pair of benchmarks differs on at least two SNC axes, even when sharing the same task label, and that resolved runs tend to involve less distributed changes and lower centrality values, with patch sizes varying between Claude and Qwen configurations. The authors recommend that practitioners choose evaluation tasks based on change characteristics, inspect task descriptions, and assess patch scope alongside test outcomes to better align benchmarks with real‑world workloads.
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.
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.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
arXiv:2608.29675v1 Announce Type: cross Abstract: Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository f...