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:2607. 28591v1 Announce Type: cross Abstract: Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation.
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification.
The paper introduces ORACLE‑SWE, a study that systematically evaluates how different intermediate information signals—such as Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage—contribute to the success of language‑model agents on software engineering tasks. It quantifies the impact of both oracle‑provided signals and those extracted by agents, and measures the performance gap between current agent‑found signals and their oracle counterparts. The authors release code and a dataset to support future signal‑analysis research in this area.
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:2607. 02469v1 Announce Type: cross Abstract: Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior.
arXiv:2605. 02411v2 Announce Type: replace Abstract: A semantic gap separates how users describe tasks from how tools are documented.
Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolving, so it remains unclear how m...
arXiv:2606. 08500v1 Announce Type: cross Abstract: Software engineering agents (SWE agents) increasingly work through tool-mediated trajectories in real repositories, yet their behavior remains difficult to characterize in concrete, observable terms.
MemDev-Bench is a new benchmark that evaluates how memory systems influence code agents across diverse repository histories. It pairs each task with relevance‑annotated earlier tasks from the same repository, creating 4,869 historical tasks for 555 base tasks and an automated pipeline that ensures these tasks are executable and verifiable. The study finds that memory mainly improves fine‑grained localization and editing, but can also cause failures when agents reuse memory without reassessing its applicability, and that providing raw historical trajectories reduces steps more effectively than compressed memories.
arXiv:2606. 30573v1 Announce Type: new Abstract: We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks.
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...
arXiv:2606. 18733v1 Announce Type: cross Abstract: Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection.