LIVE · 05/15
clineREL「CLI v3.0.3」 (cline-releases) の cline 関連アップデートCLI v3.0.3[cline-releases]copilotREL「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連ア…Timestamp fields in GitHub Projects[github-changelog]clineREL「nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751」 …nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751[cline-releases]copilotREL「Team-level Copilot usage metrics now available via API」 (github-chang…Team-level Copilot usage metrics now available via API[github-changelog]copilotREL「GitHub Actions: Upcoming image migrations」 (github-changelog) の copil…GitHub Actions: Upcoming image migrations[github-changelog]clineREL「nightly-dpc-sdk-migration-simpler-login-20260514182149-12b9b3c94afb」 …nightly-dpc-sdk-migration-simpler-login-20260514182149-12b9b3c94afb[cline-releases]copilotREL「GitHub Copilot app is now available in technical preview」 (github-cha…GitHub Copilot app is now available in technical preview[github-changelog]research「Neural Code Translation of Legacy Code: APL to C#」 (arxiv-cs-se) の re…Neural Code Translation of Legacy Code: APL to C#[arxiv-cs-se]research「Bidirectional Empowerment of Metamorphic Testing and Large Language M…Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey[arxiv-cs-se]research「A Non-Destructive Methodological Framework for Modernizing Legacy Cli…A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study[arxiv-cs-se]research「CA2: Code-Aware Agent for Automated Game Testing」 (arxiv-cs-se) の res…CA2: Code-Aware Agent for Automated Game Testing[arxiv-cs-se]research「Case Studies and Reflections on Agentic Software Engineering for Rapi…Case Studies and Reflections on Agentic Software Engineering for Rapid Development of Digital Music Instruments[arxiv-cs-se]research「CRANE: Constrained Reasoning Injection for Code Agents via Nullspace …CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing[arxiv-cs-se]research「LLM-Based Robustness Testing of Microservice Applications: An Empiric…LLM-Based Robustness Testing of Microservice Applications: An Empirical Study[arxiv-cs-se]research「Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs」 (arxiv-…Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs[arxiv-cs-se]research「Making OpenAPI Documentation Agent-Ready: Detecting Documentation and…Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System[arxiv-cs-se]research「Correctness-Aware Repository Filtering Under Maximum Effective Contex…Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints[arxiv-cs-se]research「SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Packag…SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades[arxiv-cs-se]research「FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing」 (arxi…FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing[arxiv-cs-se]research「When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Rep…When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context[arxiv-cs-se]research「Not All RAGs Are Created Equal: A Component-Wise Empirical Study for …Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks[arxiv-cs-se]research「Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for…Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation[arxiv-cs-se]research「Mining Subscenario Refactoring Opportunities in Behaviour-Driven Soft…Mining Subscenario Refactoring Opportunities in Behaviour-Driven Software Test Suites: ML Classifiers and LLM-Judge Baselines[arxiv-cs-se]research「In-IDE Toolkit for Developers of AI-Based Features」 (arxiv-cs-se) の r…In-IDE Toolkit for Developers of AI-Based Features[arxiv-cs-se]
Today 332
Total 227
Major 3
Active sources 12/51
Updated 1m ago
Daily Summary

今日の更新

Today's Updates

Today 332 ▲ 3%
Yesterday 322
7-day 836
Last 7 days
5
7
38
48
84
322
332
05/09 05/10 05/11 05/12 05/13 05/14 05/15

過去日のカウントは保持ポリシー(per-source cap / half-life)により縮む場合があります。直近 1〜2 日の活動量の目安としてご覧ください。 Past-day counts may shrink over time due to retention (per-source cap / half-life). Use this chart as a rough gauge of the last 1-2 days.

Last 7 days article counts
DateCount
2026-05-095
2026-05-107
2026-05-1138
2026-05-1248
2026-05-1384
2026-05-14322
2026-05-15332
主要な更新 Top stories 05/15 · 10 件 重要Important RELリリースRelease
  1. 01 cline REL 「CLI v3.0.3」 (cline-releases) の cline 関連アップデート CLI v3.0.3 「CLI v3.0.3」 (cline-releases) の cline 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 Add --worktree flag that auto-creates a fresh git worktree under ~/.cline/worktrees/ and runs the task there. Works with --taskId and --continue so you can resume a task in an isolated worktree to try [cline-releases]
  2. 02 copilot REL 「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連ア… Timestamp fields in GitHub Projects 「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 GitHub Projects now includes three built-in timestamp fields: Created, Updated, and Closed. You can add them to any project view to sort and filter work based on when it was… The post Timestamp fields [github-changelog]
  3. 03 cline REL 「nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751」 … nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751 「nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751」 (cline-releases) の cline 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 Cline Nightly published from dpc/sdk-migration-simpler-login at 51c8d… [cline-releases]
  4. 04 copilot REL 「Team-level Copilot usage metrics now available via API」 (github-chang… Team-level Copilot usage metrics now available via API 「Team-level Copilot usage metrics now available via API」 (github-changelog) の copilot 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 The Copilot usage metrics API now exposes a new user-teams report that maps each Copilot-licensed user to the teams they belong to. By joining the user-teams report with the existing… The post Team-le [github-changelog]
  5. 05 research 「Neural Code Translation of Legacy Code: APL to C#」 (arxiv-cs-se) の re… Neural Code Translation of Legacy Code: APL to C# 「Neural Code Translation of Legacy Code: APL to C#」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 arXiv:2605.13896v1 Announce Type: new Abstract: Automatic translation between programming languages remains a challenging problem, particularly when the source language is highly concise and specializ [arxiv-cs-se]
  6. 06 research 「Bidirectional Empowerment of Metamorphic Testing and Large Language M… Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey 「Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 arXiv:2605.13898v1 Announce Type: new Abstract: Large language models (LLMs) have introduced substantial challenges to software quality assurance due to their generative, probabilistic, and open-ended [arxiv-cs-se]
  7. 07 tech-news 「From one classroom to a nationwide movement: Advancing AI skills in T… From one classroom to a nationwide movement: Advancing AI skills in Thailand 「From one classroom to a nationwide movement: Advancing AI skills in Thailand」 (microsoft-source) の tech-news 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。 The post From one classroom to a nationwide movement: Advancing AI skills in Thailand appeared first on Source . [microsoft-source]
  8. 08 claude Claudeと90分壁打ちして4事業の優先度を1枚のシートに整理した話 JA Claudeと90分壁打ちして4事業の優先度を1枚のシートに整理した話 Claude Cowork を社内AXに使っている私の実践ログです。社内固有名・個人名は伏せています。 「この施策、今期やるべき?」って誰かに聞かれるたびに、感覚で答えてしまっていた。 1事業なら、まだいい。でも複数のラインが並行して動き出 [qiita-claude]
  9. 09 claude Claude for Small Business入門 — QuickBooks・HubSpot・M365に繋がる15ワークフロー全解説 JA Claude for Small Business入門 — QuickBooks・HubSpot・M365に繋がる15ワークフロー全解説 はじめに 2026年5月13日、Anthropicは中小企業(SMB)向けの新パッケージ 「Claude for Small Business」 を発表しました。QuickBooks、PayPal、HubSpotなど7つのビジネスツールと連 [qiita-claude]
  10. 10 cursor AIコードレビュー結果を「やりっぱなし」にしないために、Cursor スキル + gh で運用フローを作った話 JA AIコードレビュー結果を「やりっぱなし」にしないために、Cursor スキル + gh で運用フローを作った話 TL;DR AI レビューの出力を GitHub の PR 本文 / 行コメントに残す までを 1 つのワークフローにまとめたい そこで Cursor の「スキル」として ai-pr-review-tooling を作成 ポイントは 3 つ [qiita-cursor]
🔥 Today's Top 3 importance × recency
  1. 「CLI v3.0.3」 (cline-releases) の cline 関連アップデート CLI v3.0.3 cline-releases 15h ago
  2. 「Cline Releases v3.83.0」 (cline-releases) の cline 関連アップデート Cline Releases v3.83.0 cline-releases 1d ago
  3. 「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連ア… Timestamp fields in GitHub Projects github-changelog 1h ago

Timeline 227 total · page 1/8

TODAY 30 entries
NEW blog tech-news 1h ago · microsoft-source

「From one classroom to a nationwide movement: Advancing AI skills in T… From one classroom to a nationwide movement: Advancing AI skills in Thailand

AI要約 「From one classroom to a nationwide movement: Advancing AI skills in Thailand」 (microsoft-source) の tech-news 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN The post From one classroom to a nationwide movement: Advancing AI skills in Thailand appeared first on Source .

news.microsoft.com
From one classroom to a nationwide movement: Advancing AI skills in Thailand og
NEW changelog copilot 1h ago · github-changelog

「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連ア… Timestamp fields in GitHub Projects

AI要約 「Timestamp fields in GitHub Projects」 (github-changelog) の copilot 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN GitHub Projects now includes three built-in timestamp fields: Created, Updated, and Closed. You can add them to any project view to sort and filter work based on when it was… The post Timestamp fields

github.blog
Timestamp fields in GitHub Projects og
NEW blog claude 2h ago · qiita-claude

Claudeと90分壁打ちして4事業の優先度を1枚のシートに整理した話 JA Claudeと90分壁打ちして4事業の優先度を1枚のシートに整理した話

AI要約 Claude Cowork を社内AXに使っている私の実践ログです。社内固有名・個人名は伏せています。 「この施策、今期やるべき?」って誰かに聞かれるたびに、感覚で答えてしまっていた。 1事業なら、まだいい。でも複数のラインが並行して動き出

qiita.com
Claudeと90分壁打ちして4事業の優先度を1枚のシートに整理した話 og
NEW blog claude 2h ago · qiita-claude

Claude for Small Business入門 — QuickBooks・HubSpot・M365に繋がる15ワークフロー全解説 JA Claude for Small Business入門 — QuickBooks・HubSpot・M365に繋がる15ワークフロー全解説

AI要約 はじめに 2026年5月13日、Anthropicは中小企業(SMB)向けの新パッケージ 「Claude for Small Business」 を発表しました。QuickBooks、PayPal、HubSpotなど7つのビジネスツールと連

qiita.com
Claude for Small Business入門 — QuickBooks・HubSpot・M365に繋がる15ワークフロー全解説 og
NEW blog claude 4h ago · qiita-claude

【速報】NotionがAIエージェントの「ハブ」になった!100万体以上のAIが動くプラットフォームの全貌 JA 【速報】NotionがAIエージェントの「ハブ」になった!100万体以上のAIが動くプラットフォームの全貌

AI要約 結論から言うと Notionがついに「AIエージェントのハブ」になった。 2日前(5月13日)、Notionが開発者プラットフォーム3.5を発表。これにより、Claude、Codex、自作AIエージェントをNotionに接続し、ワークスペー

qiita.com
【速報】NotionがAIエージェントの「ハブ」になった!100万体以上のAIが動くプラットフォームの全貌 og
NEW blog claude 4h ago · qiita-claude

Claude Code の /advisor で Sonnet に Opus の知性を借りる JA Claude Code の /advisor で Sonnet に Opus の知性を借りる

AI要約 はじめに Claude Code で長めのタスクを回していると、ふだんは Sonnet で十分なのに「ここだけは Opus に判断してほしい」という瞬間がたまにあります。そういうときにモデル全体を Opus に切り替えるとコストも待ち時間も

qiita.com
Claude Code の /advisor で Sonnet に Opus の知性を借りる og
NEW blog cursor 7h ago · qiita-cursor

AIコードレビュー結果を「やりっぱなし」にしないために、Cursor スキル + gh で運用フローを作った話 JA AIコードレビュー結果を「やりっぱなし」にしないために、Cursor スキル + gh で運用フローを作った話

AI要約 TL;DR AI レビューの出力を GitHub の PR 本文 / 行コメントに残す までを 1 つのワークフローにまとめたい そこで Cursor の「スキル」として ai-pr-review-tooling を作成 ポイントは 3 つ

qiita.com
AIコードレビュー結果を「やりっぱなし」にしないために、Cursor スキル + gh で運用フローを作った話 og
NEW release cline 9h ago · cline-releases

「nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751」 … nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751

AI要約 「nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751」 (cline-releases) の cline 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN Cline Nightly published from dpc/sdk-migration-simpler-login at 51c8d…

github.com
nightly-dpc-sdk-migration-simpler-login-20260515043306-51c8d069a751 media
NEW paper research 10h ago · arxiv-cs-se

「Neural Code Translation of Legacy Code: APL to C#」 (arxiv-cs-se) の re… Neural Code Translation of Legacy Code: APL to C#

AI要約 「Neural Code Translation of Legacy Code: APL to C#」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.13896v1 Announce Type: new Abstract: Automatic translation between programming languages remains a challenging problem, particularly when the source language is highly concise and specializ

arxiv.org
Neural Code Translation of Legacy Code: APL to C# og
NEW paper research 10h ago · arxiv-cs-se

「Bidirectional Empowerment of Metamorphic Testing and Large Language M… Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey

AI要約 「Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.13898v1 Announce Type: new Abstract: Large language models (LLMs) have introduced substantial challenges to software quality assurance due to their generative, probabilistic, and open-ended

arxiv.org
Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey og
NEW paper research 10h ago · arxiv-cs-se

「A Non-Destructive Methodological Framework for Modernizing Legacy Cli… A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study

AI要約 「A Non-Destructive Methodological Framework for Modernizing Legacy Clinical Reporting Systems for AI-Driven Pharmacoinformatics: A SAS Case Study」 (arxiv-cs-se) の research 関連アップデー…

EN arXiv:2605.13905v1 Announce Type: new Abstract: Drug development and pharmacovigilance are frequently bottlenecked by legacy clinical reporting pipelines. These monolithic systems encode regulatory-gr

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「CA2: Code-Aware Agent for Automated Game Testing」 (arxiv-cs-se) の res… CA2: Code-Aware Agent for Automated Game Testing

AI要約 「CA2: Code-Aware Agent for Automated Game Testing」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.13918v1 Announce Type: new Abstract: Automated game testing is important for verifying game functionality, but it remains a costly and time-consuming process. Manual testing often misses ed

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Case Studies and Reflections on Agentic Software Engineering for Rapi… Case Studies and Reflections on Agentic Software Engineering for Rapid Development of Digital Music Instruments

AI要約 「Case Studies and Reflections on Agentic Software Engineering for Rapid Development of Digital Music Instruments」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文…

EN arXiv:2605.14016v1 Announce Type: new Abstract: The article explores the use of agentic software engineering (ASE) in the development of innovative audio software. It begins with a review of backgroun

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「CRANE: Constrained Reasoning Injection for Code Agents via Nullspace … CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

AI要約 「CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14084v1 Announce Type: new Abstract: Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capab

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「LLM-Based Robustness Testing of Microservice Applications: An Empiric… LLM-Based Robustness Testing of Microservice Applications: An Empirical Study

AI要約 「LLM-Based Robustness Testing of Microservice Applications: An Empirical Study」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14202v1 Announce Type: new Abstract: Malformed, missing, or boundary-value inputs in microservice APIs can cascade across dependent services, threatening reliability. Robustness testing sys

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs」 (arxiv-… Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs

AI要約 「Failure-Guided Fuzzing for Hybrid Quantum-Classical Programs」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14219v1 Announce Type: new Abstract: Hybrid quantum-classical (HQC) algorithms, such as the Variational Quantum Eigensolver (VQE) and the Quantum Approximate Optimization Algorithm (QAOA),

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Making OpenAPI Documentation Agent-Ready: Detecting Documentation and… Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System

AI要約 「Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文…

EN arXiv:2605.14312v1 Announce Type: new Abstract: The growing adoption of AI agents and the Model Context Protocol (MCP) has motivated organizations to expose existing REST APIs as agent-consumable tool

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Correctness-Aware Repository Filtering Under Maximum Effective Contex… Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints

AI要約 「Correctness-Aware Repository Filtering Under Maximum Effective Context Window Constraints」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14362v1 Announce Type: new Abstract: Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models degra

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Packag… SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades

AI要約 「SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14415v1 Announce Type: new Abstract: Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolutio

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing」 (arxi… FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

AI要約 「FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14431v1 Announce Type: new Abstract: Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Rep… When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context

AI要約 「When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14478v1 Announce Type: new Abstract: Context: Retrieval-augmented code generation relies on cross-file repository context, but retrieved snippets may come from obsolete project states. Obje

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Not All RAGs Are Created Equal: A Component-Wise Empirical Study for … Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks

AI要約 「Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14503v1 Announce Type: new Abstract: While Retrieval-Augmented Generation (RAG) is increasingly adopted to ground Large Language Models (LLMs) in software artifacts, the optimal configurati

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for… Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation

AI要約 「Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成…

EN arXiv:2605.14563v1 Announce Type: new Abstract: Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agen

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Mining Subscenario Refactoring Opportunities in Behaviour-Driven Soft… Mining Subscenario Refactoring Opportunities in Behaviour-Driven Software Test Suites: ML Classifiers and LLM-Judge Baselines

AI要約 「Mining Subscenario Refactoring Opportunities in Behaviour-Driven Software Test Suites: ML Classifiers and LLM-Judge Baselines」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の …

EN arXiv:2605.14568v1 Announce Type: new Abstract: Context. Behaviour-Driven Development (BDD) software test suites accumulate duplicated step subsequences. Three published refactoring patterns are avail

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「In-IDE Toolkit for Developers of AI-Based Features」 (arxiv-cs-se) の r… In-IDE Toolkit for Developers of AI-Based Features

AI要約 「In-IDE Toolkit for Developers of AI-Based Features」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14612v1 Announce Type: new Abstract: AI-enabled features built on LLMs and agentic workflows are difficult to test, debug, and reproduce, especially for product-focused software engineers w

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Documentation-Guided Agentic Codebase Migration from C to Rust」 (arxi… Documentation-Guided Agentic Codebase Migration from C to Rust

AI要約 「Documentation-Guided Agentic Codebase Migration from C to Rust」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14634v1 Announce Type: new Abstract: Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Agentic AI in Industry: Adoption Level and Deployment Barriers」 (arxi… Agentic AI in Industry: Adoption Level and Deployment Barriers

AI要約 「Agentic AI in Industry: Adoption Level and Deployment Barriers」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14675v1 Announce Type: new Abstract: Agentic AI systems are entering software engineering workflows, yet empirical evidence on how industrial organizations actually adopt them remains spars

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Towards In-Depth Root Cause Localization for Microservices with Multi… Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought

AI要約 「Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14866v1 Announce Type: new Abstract: As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with ri

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Viverra: Text-to-Code with Guarantees」 (arxiv-cs-se) の research 関連アップ… Viverra: Text-to-Code with Guarantees

AI要約 「Viverra: Text-to-Code with Guarantees」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完されます。

EN arXiv:2605.14972v1 Announce Type: new Abstract: A fundamental limitation of Text-to-Code is that no guarantee can be obtained about the correctness of the generated code. Therefore, to ensure its corr

arxiv.org
NEW paper research 10h ago · arxiv-cs-se

「Veritas: A Semantically Grounded Agentic Framework for Memory Corrupt… Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries

AI要約 「Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries」 (arxiv-cs-se) の research 関連アップデート。AI 要約が未生成のため、後続の Worker run で本文が補完…

EN arXiv:2605.15097v1 Announce Type: new Abstract: Detecting memory corruption vulnerabilities in stripped binaries requires recovering object semantics, interprocedural propagation, and feasible trigger

arxiv.org