# SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/swe-explore-benchmarking-how-coding-agents-explore-repositories
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/swe-explore-benchmarking-how-coding-agents-explore-repositories.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-06-10T04:35:57+00:00
Episode link: https://share.transistor.fm/s/75386176
Audio file: https://media.transistor.fm/75386176/c7c85131.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/swe-explore-benchmarking-how-coding-agents-explore-repositories
Duration seconds: 1387

## Resource

🤗 Upvotes: 102 | cs.SE, cs.CL Authors: Shaoqiu Zhang, Yuhang Wang, Jialiang Liang, Yuling Shi, Wenhao Zeng, Maoquan Wang, Shilin He, Ningyuan Xu, Siyu Ye, Kai Cai, Xiaodong Gu Title: SWE-Explore: Benchmarking How Coding Agents Explore Repositories Arxiv: http://arxiv.org/abs/2606.07297v1 Abstract: Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/swe-explore-benchmarking-how-coding-agents-explore-repositories/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/swe-explore-benchmarking-how-coding-agents-explore-repositories.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.