Requirements engineering digest
A weekly record of what appeared in academic requirements engineering: arXiv cs.SE, the Requirements Engineering Journal, EMSE, SoSyM, ASE, conference and workshop proceedings, and a set of authors I follow. Each entry covers seven days and lists the papers found, with the authors’ own abstracts and a link to each source.
It is a by-product of reading I do anyway, compiled and published without review, so take it as a pointer to the literature rather than as an assessment of it. It is not a survey, it claims no completeness, and a week in which nothing relevant appeared produces no entry at all.
202612
Week 43, 2026
19-25 October 2026 · 14 papers
- Engineering Requirements for Generative AI Agents: The BARD Process Theory
- HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements
- SWE-Clar: Can Coding Agents Clarify Incomplete Client Requirements and Deliver Greenfield Software?
- When Coding Agents Outpace Review: Evaluating PRD-Driven Development in Mature Enterprise Repositories
- From Regulation to Engineering: Organizational Privacy Climate as Mediator
Show all 14 papersShow fewer
- VERA: A Responsible AI Dashboard for Assessing LLM Deployments in Light of the EU AI Act
- Are LLM-Generated Formal Specifications Faithful to Their Requirements? A Study on Bimodal Formal Specification Generation
- Validating Autoformalized Specifications via Contrapuntal Languages
- VerusEval: Evaluating LLM-Generated Verus Specifications Beyond Verifier Acceptance
- Better Specifications, Better Code: Fine-Tuning LLMs for Behavioral Contract Generation
- From Natural Language to Verified C: Verification-Guided Generation with ACSL Specifications
- AgenTest: Mining Business Rules to Test LLM Agents for Business Logic Bugs
- Automated classification of non-functional requirements twenty years later: why this isn’t a solved problem
- Teaching Agile Requirements Engineering: A Stakeholder Simulation with Generative AI
Week 42, 2026
12-18 October 2026 · 5 papers
- Between Spoilers and Guesswork: Avoiding Over-Specification in Coding Benchmarks
- FDE-Gym: The Last Mile of AI Delivery
- The Code of Theseus: Can Agents Rebuild Software from Recovered Design Documents?
- Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
- SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?
Week 41, 2026
5-11 October 2026 · 10 papers
- Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development
- Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
- Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation
- Applying Security by Design at the Point of Execution: How Governed Security Requirements Affect the Security of AI-Generated Code
- CYBERFORT: A Compliance-Chain Platform Operationalising the Cyber Resilience Act for SMEs
Show all 10 papersShow fewer
- Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents
- The EPIC Framework for Spec-Driven Development
- Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
- Leakage-Resistant Evaluation of AI-Generated Database Specifications in Specification-Driven Migration
- SpecGuard: Proving a Task Is Broken Before the Agent Cheats
Week 40, 2026
28 September - 4 October 2026 · 6 papers
- PrivDev: Mapping Static-Analysis Data Types to DPV
- Pinning Decisions Before Failure: Executable Records of Underspecified Choices in AI-Assisted Code Generation
- Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning
- CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation
- Automatically Building Machine-Checked Assurance Cases from C Codebases to Requirements
Show all 6 papersShow fewer
Week 39, 2026
21-27 September 2026 · 10 papers
- Djinnlang: Higher-Level Programming by Unambiguous Specification with an LLM in the Compiler
- Specifying and Maintaining Agentic Workflows: An Empirical Study of GitHub Agentic Workflows
- Constraint-Driven Context Engineering: Designing Domain Interfaces for AI Systems
- LLM-Assisted Workflow for Structural Difference Visualization in Evolving Software Requirements
- Developing a Unified Verification and Validation Activity Standard at JPL
Show all 10 papersShow fewer
- Specification-Driven Benchmarking for Automated Program Repair From Static Corpora to Executable Specifications
- On the Impact of Requirement Smells in LLM-Based Code Generation
- Formal Model Construction Guided by Model-Based Proof Sketches
- Provided and requested services in the specification and design of services and service-oriented architectures
- A model for integrating regulatory requirements into continuous software delivery in financial organizations
Week 38, 2026
14-20 September 2026 · 10 papers
- LLM-enabled Behavior Driven Development Workflow for Formally Verified Hardware Designs
- A11yLTLNav: Automatic Detection of Accessibility Navigation Failures
- Relationally Guided Use Case Modeling with LLMs
- Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code
- Mind the Gap: How SBOM Specification Ambiguities Lead to Divergent Software Bills of Materials. An Empirical Tool Study
Show all 10 papersShow fewer
- SWE-Proof: Can Language Models Resolve Real-World Issues with Machine-Checked Proofs?
- Code generation for legal metadata extraction: a decomposition-based in-context learning approach
- Requirements-Based Test Generation: A Comprehensive Survey
- Requirements-Driven Automated Software Testing: A Systematic Review
- Character-level Perturbations in Software Requirements: Evaluating Transformer Models Robustness Across Learning Paradigms and Classification Tasks
Week 37, 2026
7-13 September 2026 · 2 papers
Week 36, 2026
31 August - 6 September 2026 · 3 papers
Week 35, 2026
24-30 August 2026 · 12 papers
- On the Time and Frequency Domain Representations of Signals for CPS Specification
- Human-AI Collaboration in Requirements Engineering: Evidence of the Negative Effect of LLMs on Requirements Inspection
- SLICE: Specification-Level Isolation of Contract Enforcement
- Large Language Models for Requirements Engineering: A Cross-Task Empirical Evaluation
- Ontology-based Requirements Transformation
Show all 12 papersShow fewer
- Ontology-supported Design Parameter Management for Change Impact Analysis
- An Interactive Agent for Requirement-Driven Candidate Sourcing
- Secret MCP: Evidence-Bounded and Context-Isolated Design Specification Generation from Web Screenshots
- From Natural Language Requirements to Graphical User Interfaces: Automated Prototyping and Verification with Pretrained Language Models
- SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts
- Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering
- Operationalizing Regulations into Code: A Model to Enhance Governance and Compliance in LLM Selection for Software Engineering
Week 34, 2026
17-23 August 2026 · 8 papers
- The Specification Paradox: Rethinking Requirements Engineering in the Age of AI
- LadderTeam: Dual-Agent Laddering Elicitation Framework
- Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark
- An Agentic RAG and Evaluation Framework for Assurance Case Generation: Industrial Use Case for the EU Cyber Resilience Act Compliance
- Trace-Based Execution-Level Observability of VDM-SL Specifications
Week 33, 2026
10-16 August 2026 · 11 papers
- A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents
- SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories
- Simplifying Requirements Engineering in the Context of the LGPD: An LLM-Based Investigation
- From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices
- SoK: From Generation to Consumption of Privacy Documents in Software Systems
Show all 11 papersShow fewer
- Requirements-Augmented Generation for Trustworthy Acceptance Testing of LLM-Based Software
- Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline
- An Empirical Study on the Impact of Normalized Use-Case Specifications on Traceability
- Can Formal Specifications Be Synthesized from Tests Alone?
- How Powerful are LLMs in Generating Formal Program Specifications?
- Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review
Week 32, 2026
3-9 August 2026 · 29 papers
- Automatic Translation of Unstructured Requirements into Linear Temporal Logic through Large Language Models
- In Terms of Explainability: Refining Requirements for Self-Explainable Systems
- CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMs
- AI-assisted Script Management for Requirements Elicitation Interviews
- A Triple-Robustness Analysis of Retrieval-Augmented Generation for Multi-Hop Requirements Traceability
Show all 29 papersShow fewer
- Requirements-driven database evolution: A systematic literature review
- Embrace ad-hoc requirements - A characterization based on a multi-method industry study
- AI Transparency: Governance Compliance or Stakeholder Requirements?
- A Taxonomy of Human-Robot Teamwork Requirements
- From Business Problems to AI Solutions: Where Does Transformation Support Fail?
- From Community Forums to Issue Trackers: A Moodle Case Study
- From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems
- From Quality Properties to Practice: A Guideline and Workflow for Explainability Requirements
- HM-Req: A Framework for Embedding Values within CPS Human Monitoring Requirements
- How Requirements Quality Makes (or Breaks) Traceability Link Recovery
- Writing Better Software Explanations: A Guideline-Based Approach
- Agentic Persona Generation with Critique-Refinement: An Industrial Evaluation
- From Regulation to Requirements: An Automated Requirement Derivation and Explanation Pipeline
- Supporting the Adoption of Privacy-Enhancing Technologies through Requirements Engineering
- Automated Alignment between Elicitation Interviews and Requirements
- Information is all you need: Requirements Engineering Quality Reframed
- Transforming Privacy Artifacts into Accessible Reports for Non-Technical Stakeholders
- Classification of quality characteristics in online user feedback using linguistic analysis, crowdsourcing and LLMs
- Exploring Ethical Concerns of Mobile Applications from App Reviews: A Literature Survey
- From Law to Gherkin: A Human-Centred Quasi-Experiment on the Quality of LLM-Generated Behavioural Specifications from Food-Safety Regulations
- Generative AI for Requirements Engineering: A Systematic Literature Review
- Decoupling in AI Ethics: Learning how to Walk the Talk
- From Missile Warhead to Smart Fridge: Interviews With Industry Experts on Tracing Safety- And Security-Relevant Artifacts
- Cognitive Implications of Using GenAI in Design Thinking: Insights From Educational Case Studies