arXiv cs.SE

Software Engineering daily digest.

52 past editions, oldest first by date. Atom feed → · all categories

01 — Past editions

most recent first

2026-07-19 MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in... 6 papers · No. 58
2026-07-18 MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in... 6 papers · No. 57
2026-07-17 MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in... 6 papers · No. 56
2026-07-16 Early Adoption of Agentic Coding Tools by GitHub Projects 3 papers · No. 55
2026-07-15 Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned... 9 papers · No. 54
2026-07-14 Evaluating RE Practices for Explainability: Synthesizing Insights from... 7 papers · No. 53
2026-07-13 Failure as a Process: An Anatomy of CLI Coding Agent Trajectories 9 papers · No. 52
2026-07-12 ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation 4 papers · No. 51
2026-07-11 ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation 4 papers · No. 50
2026-07-10 ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation 4 papers · No. 49
2026-07-09 Progressive Crystallization: Turning Agent Exploration into Deterministic,... 4 papers · No. 48
2026-07-08 Industry Classification of GitHub Repositories Using the North American... 12 papers · No. 47
2026-07-07 Three-Phase Evaluation of AI-Assisted Software Development Life Cycle 5 papers · No. 46
2026-07-06 TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution 7 papers · No. 45
2026-07-05 TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution 7 papers · No. 44
2026-07-04 TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution 7 papers · No. 43
2026-07-03 TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution 7 papers · No. 42
2026-07-02 Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents? 7 papers · No. 41
2026-07-01 Interface-Variant Dynamics in Software Ecosystems: Resolver-Induced... 3 papers · No. 40
2026-06-30 MCP Server Architecture Patterns for LLM-Integrated Applications 3 papers · No. 39
2026-06-29 Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in... 3 papers · No. 38
2026-06-28 The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced... 4 papers · No. 37
2026-06-27 The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced... 4 papers · No. 36
2026-06-26 The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced... 4 papers · No. 35
2026-06-25 Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study 4 papers · No. 34
2026-06-24 Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census... 3 papers · No. 33
2026-06-23 Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop... 1 papers · No. 32
2026-06-22 Probe-and-Refine Tuning of Repository Guidance for Coding Agents 6 papers · No. 31
2026-06-21 Probe-and-Refine Tuning of Repository Guidance for Coding Agents 6 papers · No. 30
2026-06-20 Probe-and-Refine Tuning of Repository Guidance for Coding Agents 6 papers · No. 29
2026-06-19 Probe-and-Refine Tuning of Repository Guidance for Coding Agents 6 papers · No. 28
2026-06-18 Where Did the Variability Go? From Vibe Coding to Product Lines by Regeneration 3 papers · No. 27
2026-06-17 All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Code 6 papers · No. 26
2026-06-16 Selection Without Signal, Recovery Through Expression: A Measurement Study... 3 papers · No. 25
2026-06-15 Empowering Student Debugging in Parallel Programming with Execution Traces... 6 papers · No. 24
2026-06-14 Understanding the Rejection of Fixes Generated by Agentic Pull Requests --... 4 papers · No. 23
2026-06-13 Understanding the Rejection of Fixes Generated by Agentic Pull Requests --... 4 papers · No. 22
2026-06-12 Understanding the Rejection of Fixes Generated by Agentic Pull Requests --... 4 papers · No. 21
2026-06-11 Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study 4 papers · No. 20
2026-06-10 From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot 1 papers · No. 19
2026-06-09 FASE: Fast Adaptive Semantic Entropy for Code Quality 3 papers · No. 18
2026-06-08 Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills 3 papers · No. 17
2026-06-07 Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under... 4 papers · No. 16
2026-06-06 Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under... 4 papers · No. 15
2026-06-05 Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under... 4 papers · No. 14
2026-06-02 Monitoring Agentic Systems Before They're Reliable 1 papers · No. 13
2026-05-30 Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review... 5 papers · No. 12
2026-05-28 Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation 4 papers · No. 11
2026-05-27 EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial... 5 papers · No. 10
2026-05-25 AI Assurance: A Comprehensive Testing Strategy for Enterprise AI Systems 6 papers · No. 9
2026-05-23 Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents 3 papers · No. 8
2026-05-22 Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents 3 papers · No. 7

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.