# Requirements

Software requirements is the discipline of identifying, documenting, and managing the conditions and capabilities that software systems must satisfy.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Inside the AI software factory: Where accessibility is won or lost

DevFeed: [Inside the AI software factory: Where accessibility is won or lost](<https://devfeed.tech/articles/inside-the-ai-software-factory-where-accessibility-is-won-or-lost-147465.md>)

Original publisher: [Read original article](<https://www.deque.com/blog/inside-the-ai-software-factory-where-accessibility-is-won-or-lost/>)

Author: Dylan Barrell

Published: 2026-11-19T13:28:07Z

Content type: article

Language: en

Sources: [Deque](<https://devfeed.tech/sources/deque.md>)

Topics: [Web Accessibility (a11y)](<https://devfeed.tech/topics/web-accessibility.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Web Content Accessibility Guidelines](<https://devfeed.tech/topics/web-content-accessibility-guidelines.md>), [axe-core](<https://devfeed.tech/topics/axe-core.md>), [Software Process](<https://devfeed.tech/topics/software-process.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [aria](<https://devfeed.tech/topics/aria.md>), [axe MCP Server](<https://devfeed.tech/topics/axe-mcp-server.md>), [Tech Debt](<https://devfeed.tech/topics/tech-debt.md>)

Tags: [a11y-for-developers](<https://devfeed.tech/tags/a11y-for-developers.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessibility-requirements](<https://devfeed.tech/tags/accessibility-requirements.md>), [accessibility-testing](<https://devfeed.tech/tags/accessibility-testing.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [ai-workflows](<https://devfeed.tech/tags/ai-workflows.md>), [assistive-technology](<https://devfeed.tech/tags/assistive-technology.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audits](<https://devfeed.tech/tags/audits.md>), [automation](<https://devfeed.tech/tags/automation.md>), [axe-core](<https://devfeed.tech/tags/axe-core.md>), [digital-accessibility](<https://devfeed.tech/tags/digital-accessibility.md>), [risk](<https://devfeed.tech/tags/risk.md>), [shift-left](<https://devfeed.tech/tags/shift-left.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>), [technical-debt](<https://devfeed.tech/tags/technical-debt.md>)

### AI overview

The article argues that accessibility should be built into AI software factories from the start, because late fixes increase rework and production fixes are reported to cost 30 times more than design fixes. It recommends accessibility criteria in UI tickets; deterministic checks such as Axe-core and lint rules wherever possible; agents steered with relevant context and integration tests; independent test records tied to the code; and monitoring, audits, and customer feedback after release. Use AI for judgment calls, such as whether a label fits its context, and rules based tools for repeatable checks. In the article's preliminary comparison, prompting was least predictable; open source tooling caught 50% of baseline audit defects, while paid tooling caught 69%, with fewer reported false positives and more consistent results. The authors say homegrown tools require maintenance and expertise. Automation still misses issues: end to end journeys, real assistive technology use, and human review remain necessary. Measure missed production issues and the share of UI changes with accessibility evidence, and feed recurring problems back into factory rules and tests.

### Source excerpt

As your organization moves development into AI software factories, you must fully embed digital accessibility, just as you must integrate privacy and security. Get it right, and your products, services, and experiences become and stay accessible. Get it wrong, and you increase risk, cost, and technical debt. The post Inside the AI software factory: Where accessibility is won or lost appeared first on Deque.

## Controlled Natural Language for Requirements Specification: A Systematic Literature Review

DevFeed: [Controlled Natural Language for Requirements Specification: A Systematic Literature Review](<https://devfeed.tech/articles/controlled-natural-language-for-requirements-specification-a-systematic-literature-review-142136.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23259>)

Author: Ikram Darif (Department of Software and IT Engineering, Ecole de technologie superieure, Montreal, Canada), Ghizlane El Boussaidi (Department of Software and IT Engineering, Ecole de technologie super

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [cs-se](<https://devfeed.tech/tags/cs-se.md>), [language](<https://devfeed.tech/tags/language.md>), [literature](<https://devfeed.tech/tags/literature.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [review](<https://devfeed.tech/tags/review.md>), [specification](<https://devfeed.tech/tags/specification.md>)

### AI overview

The review analyzes 133 studies published from 2000 to 2024 on controlled natural languages (CNLs) for specifying software requirements. It categorizes approaches into standalone templates, requirement patterns, elementary templates, and linguistic rules, and compares them across context, scope, requirement types, specification technique, tool support, validation, and adoption. The authors report limited automated tool support and domain vocabulary use, few case-study validations, and limited adoption for most approaches. CNLs aim to make requirements both understandable to stakeholders and precise enough for automated processing, bridging natural and formal languages.

### Source excerpt

arXiv:2611.23259v1 Announce Type: new Abstract: Requirements are critical artifacts of the software development life-cycle. They express capabilities that the system should provide, guiding both the development and testing process. Given their significance, require- ments specification has attracted the interest of researchers and practitioners in recent years. Requirements specification is an activity where requirements are specified, i.e., documented. In this context, Controlled Natural Languages (CNL) were proposed as a compromise between the ambiguity of natural language and the complexity of formal languages. CNLs enable the specification of requirements using accurate statements that can be processed automatically, while remaining understandable by stakeholders. In this article, we perform a Systematic Literature Review (SLR) to identify, categorize, and compare CNL approaches for requirements specification. The SLR covers 133 primary studies published between 2000 and 2024. We evaluate them accord- ing to seven dimensions: context, scope, targeted requirements types, specification technique, tool support, validation method, and adoption. We provide a categorization framework that summarizes the evaluated dimensions, and we identify directions for future research. Our main results reveal: (1) four types of CNL: standalone templates, requirement patterns, elementary templates, and linguistic rules, (2) limited support for automated tools and domain vocabulary usage, and (3) lack of validation through case studies and limited adoption for the majority of approaches.

## Systematic Mapping Protocol. Generative AI-Augmented Requirements Engineering: A Systematic Mapping Study of Practices, Specifications, and Reuse in Software Development

DevFeed: [Systematic Mapping Protocol. Generative AI-Augmented Requirements Engineering: A Systematic Mapping Study of Practices, Specifications, and Reuse in Software Development](<https://devfeed.tech/articles/systematic-mapping-protocol-generative-ai-augmented-requirements-engineering-a-systematic-mapping-study-of-practices-specifications-and-reuse-in-software-development-142182.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23349>)

Author: Fernando Pinciroli

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-extraction](<https://devfeed.tech/tags/data-extraction.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [mapping](<https://devfeed.tech/tags/mapping.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [requirements-engineering](<https://devfeed.tech/tags/requirements-engineering.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [specifications](<https://devfeed.tech/tags/specifications.md>), [threats](<https://devfeed.tech/tags/threats.md>), [transparency](<https://devfeed.tech/tags/transparency.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

The document sets out a protocol for a systematic mapping study of generative AI in requirements engineering, focusing on the specifications it produces and how those work products are used downstream. It asks how they support activities such as specification-driven development, design and code generation, test derivation, verification, and reuse. The protocol specifies research questions and classification schemes, search and study selection procedures, data extraction and analysis, tool support, and threats to validity. Published in advance, it aims to establish prior commitment and make the planned study transparent and repeatable; it reports a protocol, not mapping results.

### Source excerpt

arXiv:2611.23349v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI), particularly large language models (LLMs), is rapidly being adopted in requirements engineering (RE). Existing secondary studies have characterized which RE activities are supported and which prompting strategies are used, but little is known about the specifications that GenAI-augmented RE produces and how they are used in subsequent activities such as specification-driven development (SDD), design and code generation, test derivation, verification, and reuse. This document presents the protocol of a systematic mapping study (SMS) that will identify and classify research on GenAI-augmented RE, with particular attention to the work products it generates and their downstream use. The protocol defines the research questions and their classification schemes, the search strategy, the study selection procedure, the data extraction form, the analysis approach, the tool support, and the threats to validity. It is published in advance to establish a prior commitment and to support the transparency and repeatability of the study.

## Ask the Peers: Ranking NFR Coverage Gaps for Requirements Review

DevFeed: [Ask the Peers: Ranking NFR Coverage Gaps for Requirements Review](<https://devfeed.tech/articles/ask-the-peers-ranking-nfr-coverage-gaps-for-requirements-review-142160.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23296>)

Author: Risha Parveen, Najmeh Akbari, Farnaz Delirie, Zheying Zhang, Fran\\c{c}ois Christophe, Jussi Rasku, Pekka Abrahamsson

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [analyst](<https://devfeed.tech/tags/analyst.md>), [categories](<https://devfeed.tech/tags/categories.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [gap](<https://devfeed.tech/tags/gap.md>), [peer](<https://devfeed.tech/tags/peer.md>), [project](<https://devfeed.tech/tags/project.md>), [ranking](<https://devfeed.tech/tags/ranking.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [review](<https://devfeed.tech/tags/review.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [specification](<https://devfeed.tech/tags/specification.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [structured](<https://devfeed.tech/tags/structured.md>)

### AI overview

The study ranks 11 PROMISE non-functional requirement categories to flag possible coverage gaps for analyst review. It compares seven statistical, embedding-based, and LLM configurations using target requirements, peer requirements, semantic representations, and peer category statistics, evaluated with controlled gap injection and leave-one-project-out testing across PROMISE, PROMISE+, PURE-Transport, and PURE-Business. Under complete category removal, four configurations using peer statistics are effectively tied at 0.875-0.889 mean AUROC; giving those statistics to a direct LLM ranker yields the largest evidence gain. Performance weakens when categories are present but underrepresented, and no configuration leads for every category. The results favor structured peer evidence over ranker sophistication for count-changing gaps, while positioning rankings as prompts for analyst inspection rather than automatic completeness judgments.

### Source excerpt

arXiv:2611.23296v1 Announce Type: new Abstract: Missing or underrepresented non-functional requirements (NFR) categories leave little direct evidence in a requirements set, making them difficult to identify during requirements review. In this study, we frame NFR coverage-gap review as a project-level ranking task: given a target requirements specification, the goal is to rank the 11 PROMISE NFR categories for analyst inspection. We compare seven statistical, embedding-based, and large language model (LLM)-based configurations that differ in both ranking mechanism and evidence source, including target requirement statements, peer requirements, their semantic representation, and peer category statistics. We evaluate the configurations using controlled gap injection with leave-one-project-out evaluation on PROMISE, PROMISE+, PURE-Transport, and PURE-Business. Four configurations that use peer category statistics are effectively tied under complete removal (0.875-0.889 mean AUROC), despite different ranking mechanisms, and supplying those statistics to a direct LLM ranker produces the largest evidence gain. All configurations weaken when a category is present but underrepresented, and none is best for every NFR category. For count-changing category-level gaps, structured peer evidence matters more than ranker sophistication. The findings suggest that the rankings should guide analyst inspection rather than serve as automatic judgements of requirements completeness.

## SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations

DevFeed: [SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations](<https://devfeed.tech/articles/swe-cowork-benchmarking-coding-agents-as-digital-employees-in-organizations-137548.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20218>)

Author: Xinping Lei, Minghao Liu, Ruijie Zhu, Xiaohui Hu, Xingqiao Li, Ao Zhang, Wenhao Chai, Han Li, Tao Wang, Jingyuan Zhang, Enduo Zhao, Yunfeng Shi, Yiming Liang, Zetao Yang, Xingjian Wang, Yifan Yao, Xin

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>)

Tags: [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [collaboration](<https://devfeed.tech/tags/collaboration.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [organizations](<https://devfeed.tech/tags/organizations.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

SWE-CoWork tests whether coding agents can deliver software assignments while gathering and reconciling requirements across colleagues and workplace records. Across 101 assignments in real repositories, the two leading models passed about 63% of fail-to-pass tests but completed fewer than 8% of assignments. Supplying complete requirements improved those test results by about 16 percentage points for Seed Evolving and GPT-6 Astra, without changing assignment completion. The reported failures span the workflow: Claude-Opus-5.5 directed 93% of first questions to accountable owners but obtained only 64% of colleague-held requirements; deferred questions went unfollowed, implementations remained incomplete, and 31% of requirements reported complete failed tests. The findings point to sustained tracking through clarification, implementation, verification, and handoff as a key challenge. This overview is based on the supplied abstract.

### Source excerpt

arXiv:2611.20218v1 Announce Type: cross Abstract: A coding agent working within a software organization must establish what to build, collaborate with colleagues, and verify what it delivers. We introduce SWE-CoWork, a benchmark comprising 101 development assignments across 101 real repositories, 11 programming languages, and 12 application domains. Each assignment places an agent in a simulated engineering organization with 26 colleagues who have distinct responsibilities, bounded knowledge, and controlled collaboration behavior. Starting from a brief handoff, agents must recover requirements distributed across colleagues and workplace records, reconcile conflicting evidence, and implement changes evaluated by private executable tests. We evaluate eleven models and find a substantial gap between partial implementation and complete task delivery. The two leading models satisfy approximately 63% of fail-to-pass (F2P) tests but complete fewer than 8% of assignments. Providing complete requirements upfront improves F2P by approximately 16 percentage points for Seed Evolving and GPT-6 Astra, yet leaves complete task success unchanged. Requirement-level trajectory analysis reveals failures throughout the delivery process: Claude-Opus-5.5 directs a mean of 93% of first questions about queried cards to their accountable owners across runs but obtains only 64% of colleague-held requirements. Deferred questions go unfollowed, implementations remain incomplete even after requirements are acquired, and 31% of requirements reported as completed fail their tests. These findings highlight sustained requirement tracking, from clarification through implementation, verification, and handoff, as a key challenge for reliable autonomous software engineering.

## Between Obligations and Evidence: A Participatory Study of Translating the EU AI Act into Technical Requirements

DevFeed: [Between Obligations and Evidence: A Participatory Study of Translating the EU AI Act into Technical Requirements](<https://devfeed.tech/articles/between-obligations-and-evidence-a-participatory-study-of-translating-the-eu-ai-act-into-technical-requirements-135199.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.18439>)

Author: Helma Torkamaan, Masoud Mansoury, Yanan Xin, Oscar Oviedo Trespalacios, Roberta Savella, Andrej Zwitter, Maria Heuss, Huy Son Nguyen, Marie-Therese Sekwenz, Moyi Li, Roberta Tamponi, Megha Khosla

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [ai regulation](<https://devfeed.tech/topics/ai-regulation.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [audit](<https://devfeed.tech/topics/audit.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cy](<https://devfeed.tech/tags/cs-cy.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [discrimination](<https://devfeed.tech/tags/discrimination.md>), [eu](<https://devfeed.tech/tags/eu.md>), [eu-ai-act](<https://devfeed.tech/tags/eu-ai-act.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [human-oversight](<https://devfeed.tech/tags/human-oversight.md>), [metrics](<https://devfeed.tech/tags/metrics.md>), [operational](<https://devfeed.tech/tags/operational.md>), [organizational](<https://devfeed.tech/tags/organizational.md>), [oversight](<https://devfeed.tech/tags/oversight.md>), [performance](<https://devfeed.tech/tags/performance.md>), [public](<https://devfeed.tech/tags/public.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [study](<https://devfeed.tech/tags/study.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

A participatory workshop with 32 researchers, policymakers, and practitioners found that translating the EU AI Act's high-risk system obligations into compliance requirements depends on context, and that technical measures, human oversight, and evidence validity are interdependent. Participants noted that recruitment fairness metrics could conceal discrimination, time pressure and limited information could weaken human oversight in public transport, and changing patient populations could undermine earlier performance evidence. The findings indicate that compliance requires attention to how systems are used and governed, alongside technical assessment, and ongoing monitoring as conditions change.

### Source excerpt

arXiv:2611.18439v1 Announce Type: cross Abstract: The EU AI Act imposes technical and organizational requirements for high-risk AI systems, but applying these requirements involves contextual choices about what to measure and what evidence supports a compliance claim. We investigate these challenges through a participatory workshop involving 32 researchers, policymakers, and practitioners from different disciplines, using realistic scenarios in healthcare, recruitment, and public transport to examine how regulatory obligations are interpreted, translated into technical requirements, and evaluated in practice. Through a thematic analysis of workshop data, we identify recurring tensions between how regulatory obligations are translated into measurable system properties, how responsibility and human oversight are exercised in practice, and how the validity of compliance evidence is affected by changing operational conditions and system uses. For example, participants highlighted how fairness metrics could conceal discrimination in recruitment, how time pressure and limited information could undermine human oversight in public transport, and how changes in patient populations could invalidate previously established evidence of system performance. Our findings suggest that technical, organizational, and evidentiary challenges are interdependent, and that establishing and maintaining compliance requires attention not only to technical assessments but also to how AI systems are used, governed, and monitored over time. We discuss implications for supporting context-sensitive and ongoing compliance.

## OCTAVE: A Capability-Resolved Benchmark for End-to-End HTML5 Game Generation

DevFeed: [OCTAVE: A Capability-Resolved Benchmark for End-to-End HTML5 Game Generation](<https://devfeed.tech/articles/octave-a-capability-resolved-benchmark-for-end-to-end-html5-game-generation-135097.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17681>)

Author: Kehang Li, Xinlan Xu, Yulin Jin, Heng Cao, Xuchen Li, Houxian Ren, Zihao Ji, Qiang Luo, Yadong Mao, Qilin He, Jian Zhang, Jian Zhao, Zihao Wang

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Web](<https://devfeed.tech/topics/web.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [capability](<https://devfeed.tech/tags/capability.md>), [core](<https://devfeed.tech/tags/core.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [game](<https://devfeed.tech/tags/game.md>), [generation](<https://devfeed.tech/tags/generation.md>), [html5](<https://devfeed.tech/tags/html5.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [pc](<https://devfeed.tech/tags/pc.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [source-code](<https://devfeed.tech/tags/source-code.md>), [static](<https://devfeed.tech/tags/static.md>)

### AI overview

OCTAVE evaluates end-to-end HTML5 game generation through 180 tasks and 1,800 requirements across eight capability dimensions, separating public core implementation (Completeness) from hidden system relationships (Richness). Across 11 model-harness combinations, average scores were 33.2% and 32.5%, respectively; 19.9% of generation records failed static gates or lacked artifacts. Excluding same-model self-evaluation, the best combination scored below 50% on both measures. Systems did relatively better on Core Rules and Numerical Design, with larger gaps in AI/NPC and Feedback and Game Feel. Richness was not harder in every task condition, and requirement difficulty only weakly tracked pass rates. In a limited human cross-check, the main disagreement was that humans judged requirements satisfied when the automated evaluator failed them.

### Source excerpt

arXiv:2611.17681v1 Announce Type: new Abstract: Complete game generation requires agents to coordinate rules, interactions, states, and presentation over a long development process. A single aggregate score obscures which capabilities are implemented and which requirements remain unmet. We present OCTAVE, a benchmark for complete HTML5 game generation organized around eight Capability Dimensions, with 180 tasks and 1,800 Evaluation Requirements drawn from real player requests, commercial-mechanics reconstruction, and human expert design. It covers PC Web, Mobile Web, 2D, and 3D. Requirements distinguish Completeness, assessing publicly specified core implementation, from Richness, assessing hidden, deeper system relationships. Static source-code judgments provide requirement-level diagnosis across capabilities and task conditions. Evaluation of 11 model-harness combinations yields 33.2% Completeness and 32.5% Richness; 19.9% of generation records are static gate failures or missing artifacts. Excluding same-model self-evaluation, even the best combination remains below 50% on both public and hidden requirements. Richness is not harder than Completeness under every task condition. Systems perform relatively better on Core Rules and Numerical Design, while AI/NPC and Feedback and Game Feel show more prominent gaps. Requirement difficulty offers coarse stratification but is only weakly negatively correlated with pass rates. A limited human cross-check finds that requirements judged satisfied by humans but failed by the automated evaluator are the main direction of disagreement. OCTAVE extends evaluation beyond aggregate scores to diagnosis localized by requirement, capability, and task condition.

## Non-Functional Requirements to Hyperparameter Translation for Quantum Software via LLMs

DevFeed: [Non-Functional Requirements to Hyperparameter Translation for Quantum Software via LLMs](<https://devfeed.tech/articles/non-functional-requirements-to-hyperparameter-translation-for-quantum-software-via-llms-131739.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16902>)

Author: Joseph G. Bronyah, Nasir U. Eisty

Published: 2026-11-13T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [configuration](<https://devfeed.tech/tags/configuration.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [execution](<https://devfeed.tech/tags/execution.md>), [human-oversight](<https://devfeed.tech/tags/human-oversight.md>), [llms](<https://devfeed.tech/tags/llms.md>), [quantum-software](<https://devfeed.tech/tags/quantum-software.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [simulations](<https://devfeed.tech/tags/simulations.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [speed](<https://devfeed.tech/tags/speed.md>), [time](<https://devfeed.tech/tags/time.md>), [translation](<https://devfeed.tech/tags/translation.md>), [user-stories](<https://devfeed.tech/tags/user-stories.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

In Qiskit/Aer simulations, seven LLMs translated natural-language requirements into quantum execution settings more accurately than a deterministic heuristic: on 18 real-world user stories, scores ranged from 55.6% to 83.3%, versus 16.7% for the heuristic. The study found no statistically significant winner among the LLMs on that dataset. Speed- and cost-oriented settings reduced execution time and cost, while fidelity improvements were not supported. Some failures stemmed from provider safety refusals rather than translation mistakes. The findings support potential use of LLMs for this translation task, with execution-based validation and human oversight; the supplied text is an abstract, not full paper evidence.

### Source excerpt

arXiv:2611.16902v1 Announce Type: new Abstract: Quantum software engineering (QSE) lacks validated approaches for translating natural-language non-functional requirements (NFRs) into execution parameters such as shots and transpiler optimization levels. Existing methods emphasize semantic similarity rather than execution outcomes. We evaluate seven large language models (LLMs) against a deterministic heuristic baseline using 540 synthetic and 18 real-world user stories. We assess semantic accuracy and execution outcomes, including time, cost, top-state probability, and two-qubit gate exposure, through Qiskit/Aer simulations. All LLMs significantly outperformed the heuristic in semantic accuracy, achieving 55.6 to 83.3 percent on real-world stories compared to 16.7 percent for the heuristic. However, no LLM demonstrated statistically significant superiority over others on the real-world dataset. Speed- and cost-oriented configurations reduced execution time and cost, but fidelity improvements were not supported. Some failures resulted from provider safety refusals rather than translation errors. Our findings demonstrate the potential of LLMs as middleware for NFR-to-configuration translation in QSE, while emphasizing execution-based validation, human oversight, and careful interpretation of model differences.

## Integrating MBSE Principles with AI to Improve the Quality of Requirements in SMEs Context

DevFeed: [Integrating MBSE Principles with AI to Improve the Quality of Requirements in SMEs Context](<https://devfeed.tech/articles/integrating-mbse-principles-with-ai-to-improve-the-quality-of-requirements-in-smes-context-124027.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09234>)

Author: Iryna Volosheniuk (LAAS-TRUST), Claude Baron (LAAS-TRUST), Jean-Michel Bruel (IRIT-SM@RT)

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [methodology](<https://devfeed.tech/tags/methodology.md>), [practices](<https://devfeed.tech/tags/practices.md>), [proof-of-concept](<https://devfeed.tech/tags/proof-of-concept.md>), [quality](<https://devfeed.tech/tags/quality.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [sme](<https://devfeed.tech/tags/sme.md>), [systems-engineering](<https://devfeed.tech/tags/systems-engineering.md>), [traceability](<https://devfeed.tech/tags/traceability.md>), [validation](<https://devfeed.tech/tags/validation.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

The paper proposes a lightweight MBSE methodology for SMEs that combines MBSE principles with AI-assisted analysis to refine requirements, improve traceability, and support early validation and verification. It aims to fit SME constraints and existing tools and practices. A proof of concept in an industrial case study demonstrates the feasibility of supporting early V&V and improving traceability across engineering artifacts. The abstract reports potential to support gradual MBSE adoption and improve engineering efficiency; it does not specify the AI methods or quantify the results.

### Source excerpt

arXiv:2611.09234v1 Announce Type: new Abstract: Model-Based Systems Engineering (MBSE) is a promising approach to improve systems engineering practices, particularly by enhancing requirement management, traceability, and early validation and verification (V\&V). However, its adoption remains challenging, especially for small and medium-sized enterprises (SMEs), which often lack structured processes and solutions adapted to their scale and constraints. Our goal is to propose a lightweight MBSE methodology tailored to the needs and constraints of SMEs. This paper focuses specifically on requirements refinement, traceability, and early V\&V. The approach integrates MBSE principles with artificial intelligence-assisted analysis to improve requirements quality while remaining compatible with existing tools and practices. A proof of concept is developed and applied in an industrial case study to evaluate the feasibility of the approach. The results demonstrate how early V\&V activities can be supported within an SME context, while improving traceability across engineering artifacts. These findings highlight the potential of a lightweight, integrated MBSE approach to support the progressive adoption of MBSE in SMEs, thereby improving overall engineering efficiency.

## Get to Grips with Constraints

DevFeed: [Get to Grips with Constraints](<https://devfeed.tech/articles/get-to-grips-with-constraints-123007.md>)

Original publisher: [Read original article](<https://ixdf.org/literature/article/non-functional-requirements-constraints>)

Author: William Hudson

Published: 2026-11-06T12:00:00Z

Content type: article

Language: en

Sources: [UX Daily - User Experience Daily](<https://devfeed.tech/sources/ux-daily-user-experience-daily.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [User Stories](<https://devfeed.tech/topics/user-stories.md>), [standard](<https://devfeed.tech/topics/standard.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [availability](<https://devfeed.tech/tags/availability.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [design](<https://devfeed.tech/tags/design.md>), [development](<https://devfeed.tech/tags/development.md>), [devices](<https://devfeed.tech/tags/devices.md>), [diagram](<https://devfeed.tech/tags/diagram.md>), [end-to-end-encryption](<https://devfeed.tech/tags/end-to-end-encryption.md>), [functionality](<https://devfeed.tech/tags/functionality.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [user](<https://devfeed.tech/tags/user.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>)

### AI overview

Non-functional requirements set measurable boundaries for how a product must work, and can shape user-facing design as well as implementation. The source groups constraints into technology choices, such as supported platforms, and quality-of-service characteristics, including performance, security, localization, usability, and reliability. A mobile-support decision can affect interface design; security requirements may add login or two-factor-authentication steps, while localization may require language selection. Requirements should be specific and measurable: for example, a stated task-completion target or WCAG 2.x Level AA compliance, rather than simply calling a product usable. The toaster comparison distinguishes functional requirements, such as slot configuration, from non-functional compatibility with a country's electrical system. Considering these boundaries early can reduce rework and expose functional requirements that follow from them.

### Source excerpt

Got constraints? Perfect. That's where great design begins. Just as electrical standards define how a toaster safely works without shaping what it does, your software also lives within boundaries that quietly guide its behavior. Functional requirements describe what your system does: the stories of use, the features your users see. However, non-functional requirements define how it must work: securely, accessibly, and efficiently. When you treat these constraints as design allies rather than obstacles, you make smarter choices, avoid costly rework, and build products that feel solid, consistent, and ready for anything.In this video, William Hudson, User Experience Strategist and Founder of S...

## Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline

DevFeed: [Requirements Nobody Wrote Down: Emergence in a Public-Sector ML Pipeline](<https://devfeed.tech/articles/requirements-nobody-wrote-down-emergence-in-a-public-sector-ml-pipeline-120830.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07951>)

Author: Ronivaldo Ferreira, Vinicius Costa Girard, Cleidson de Souza, Igor Steinmacher, Carla Aguiar, Filipe Roseiro Cogo, Gustavo Pinto

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [text-classification](<https://devfeed.tech/topics/text-classification.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [brazil](<https://devfeed.tech/tags/brazil.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [categories](<https://devfeed.tech/tags/categories.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [digital](<https://devfeed.tech/tags/digital.md>), [domain](<https://devfeed.tech/tags/domain.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [experimentation](<https://devfeed.tech/tags/experimentation.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [formalized](<https://devfeed.tech/tags/formalized.md>), [goals](<https://devfeed.tech/tags/goals.md>), [government](<https://devfeed.tech/tags/government.md>), [integration](<https://devfeed.tech/tags/integration.md>), [interviews](<https://devfeed.tech/tags/interviews.md>), [ml](<https://devfeed.tech/tags/ml.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [public-sector](<https://devfeed.tech/tags/public-sector.md>), [requirements](<https://devfeed.tech/tags/requirements.md>)

### AI overview

A 15-month case study of a machine-learning classification pipeline for Brazil's digital participation platform found that requirements often emerged during experiments and integration rather than being set upfront. Of 95 reconstructed requirements and criteria, only 40% were formalized; broad institutional goals were endorsed but lacked sponsorship. Government taxonomy determined the classification categories because of its institutional legitimacy. Acceptance combined technical metrics, domain judgment, and political assessment, but lacked shared thresholds and practical validation of usefulness. The authors conclude that technical and institutional artifacts help elicit requirements, and that experimentation and integration are part of requirements engineering for public-sector ML.

### Source excerpt

arXiv:2611.07951v1 Announce Type: new Abstract: Governments increasingly use machine learning (ML) to handle data volumes beyond their analytical capacity, yet little is known about how requirements arise and evolve as an ML experiment moves toward operational use. Requirements Engineering (RE) for ML often assumes that requirements can be elicited upfront; in the public sector, however, demands arrive vague, stakeholders speak different professional languages, and what counts as a ``good'' result is unknown in advance. We report a 15-month case study of a thematic classification pipeline for Brazil's national digital participation platform, which holds over 60,000 citizen proposals, triangulating 43 project artifacts with interviews of six project participants. Institutional demands arrived as broad goals, endorsed but not sponsored, and only 40\% of the 95 reconstructed requirements and criteria were ever formalized. The pipeline's key requirements emerged largely from experiments, model outputs, and integration work, shaped by technical decisions and institutional constraints; the central one, the classification categories, was settled by a government taxonomy chosen for its institutional legitimacy. Acceptance relied on technical metrics, domain judgment, and political assessment, without shared thresholds or validation of usefulness in practice. In public-sector ML, technical and institutional artifacts thus act as elicitation instruments, and experimentation and integration belong to the requirements process.

## RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection

DevFeed: [RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection](<https://devfeed.tech/articles/routealign-aligning-task-requirements-with-model-profiles-for-llm-service-selection-120833.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.08162>)

Author: Jihao Zhao, Ding Chen, Yanfang Chen, Bo Tang, Feiyu Xiong, Junchi Yan, Zhiyu Li

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [cost](<https://devfeed.tech/tags/cost.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [frontier](<https://devfeed.tech/tags/frontier.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [performance](<https://devfeed.tech/tags/performance.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [selection](<https://devfeed.tech/tags/selection.md>), [service](<https://devfeed.tech/tags/service.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

RouteAlign selects LLM services by matching task requirements--capability demand and difficulty--to model performance evidence. Historical requirements shape global profiles and local capability estimates; incoming requirements guide the current decision through a shared scorer, while a generation-cost preference controls selection among eligible services. The abstract reports that evaluations across diverse tasks and heterogeneous services extended the empirical quality-cost frontier toward higher task quality. Against open Jev-style decision backends, RouteAlign reportedly achieved consistent quality gains at lower generation cost than their strongest tested configuration. Ablations support the value of local performance evidence, and catalog-update experiments show reuse of the fitted scorer with refreshed model measurements.

### Source excerpt

arXiv:2611.08162v1 Announce Type: new Abstract: LLM service selection requires performance evidence that reflects the demands of the current task. Aggregate scores obscure differences in capability and difficulty, while semantically related examples can involve different combinations of skills. We present RouteAlign, which uses task requirements to structure both the measurement of model performance and the selection of services. Task requirements describe capability demand and difficulty, enabling alignment with corresponding model performance measurements. Historical requirements determine how outcomes contribute to global profiles and local capability estimates; incoming requirements determine how those measurements inform the current decision. A shared scorer integrates the evidence, and a generation-cost preference controls selection among eligible services. Evaluation across diverse tasks and heterogeneous LLM services shows that RouteAlign extends the empirical quality-cost frontier toward higher task quality. Comparisons with open Jev-style decision backends show consistent quality gains, with lower generation cost than their strongest tested configuration. Ablations support the contribution of local performance evidence, while catalog-update experiments demonstrate effective reuse of the fitted scorer with refreshed model measurements.

## Req2Rust: A Requirements-Guided Agent Harness for Project-Level C++-to-Rust Migration

DevFeed: [Req2Rust: A Requirements-Guided Agent Harness for Project-Level C++-to-Rust Migration](<https://devfeed.tech/articles/req2rust-a-requirements-guided-agent-harness-for-project-level-c-to-rust-migration-120814.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.07442>)

Author: Shengbo Wang, Mingwei Liu, Yuwen Chen, Yanlin Wang

Published: 2026-11-06T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Rust](<https://devfeed.tech/topics/rust.md>), [c/c++](<https://devfeed.tech/topics/c-c-plus-plus.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>)

Tags: [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [c-plus-plus-to-rust](<https://devfeed.tech/tags/c-plus-plus-to-rust.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory-safety](<https://devfeed.tech/tags/memory-safety.md>), [migration](<https://devfeed.tech/tags/migration.md>), [rust](<https://devfeed.tech/tags/rust.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [specification](<https://devfeed.tech/tags/specification.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Req2Rust uses an evidence-grounded Migration Requirements Specification (MRS) to record behaviors and constraints to preserve, then derives a Rust Design Specification (RDS) and an initial Rust project. It treats that project as an executable refinement state: compiler, semantic, and unsafe-reduction validators report issues to guide improvements in buildability, behavioral alignment, and unsafe usage. In evaluations against a ClaudeCode baseline, Req2Rust produced buildable Rust crates and raised test pass rates from 69.5% to 91.9% on general projects and from 45.4% to 87.9% on OpenHarmony modules. The supplied abstract does not detail evaluation methods or the extent of unsafe-code reduction.

### Source excerpt

arXiv:2611.07442v1 Announce Type: new Abstract: Memory-safety concerns make Rust an attractive target for modernizing legacy C/C++ systems, yet project-level C++ migration must balance semantic fidelity with Rust-oriented reconstruction. Source-structure-preserving migration can track low-level behavior, but it can also carry source-language organization, unsafe idioms, and project assumptions into Rust. Direct agent-based translation gives the model more freedom to construct a Rust project, but semantic coverage depends on the model identifying the source behaviors that must be preserved. This problem is especially acute for C++, where source behaviors are often hidden in object models, destructor-driven lifetime protocols, and other hard-to-localize C++ semantics. This paper presents Req2Rust, the first project-level LLM-based C++-to-Rust migration harness. Req2Rust first derives an evidence-grounded Migration Requirements Specification (MRS) that records the behaviors and constraints that must be preserved. It then synthesizes a Rust Design Specification (RDS) and realizes it as an initial Rust project. Because real projects contain implementation details and idioms that only become visible during build and validation, Req2Rust treats the initial Rust project as an executable refinement state. Compiler, semantic, and unsafe-reduction validators produce validation reports for improving buildability, behavioral alignment, and unsafe usage. We evaluate Req2Rust on general C++ projects and modules from the large-scale Openharmony codebase against a ClaudeCode baseline. Req2Rust produces buildable Rust crates in both settings and improves test pass rate from 69.5% to 91.9% on general projects and from 45.4% to 87.9% on Openharmony modules.

## Req-Space: A User Study of Interactive Visualisations for Requirements Review

DevFeed: [Req-Space: A User Study of Interactive Visualisations for Requirements Review](<https://devfeed.tech/articles/req-space-a-user-study-of-interactive-visualisations-for-requirements-review-118048.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05437>)

Author: Risha Parveen, Navneet Arora, Zheying Zhang, Kalle M\\"akel\\"a, Pekka Abrahamsson

Published: 2026-11-05T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [human computer interaction](<https://devfeed.tech/topics/human-computer-interaction.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [User Interfaces](<https://devfeed.tech/topics/user-interfaces.md>)

Tags: [change](<https://devfeed.tech/tags/change.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [exploration](<https://devfeed.tech/tags/exploration.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [it](<https://devfeed.tech/tags/it.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [relationships](<https://devfeed.tech/tags/relationships.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [review](<https://devfeed.tech/tags/review.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [specification](<https://devfeed.tech/tags/specification.md>), [specifications](<https://devfeed.tech/tags/specifications.md>), [study](<https://devfeed.tech/tags/study.md>), [traceability](<https://devfeed.tech/tags/traceability.md>), [user](<https://devfeed.tech/tags/user.md>)

### AI overview

Req-Space, an interactive prototype combining semantic exploration and traceability visualisation, supported human-led review of a fictional 40-requirement specification and a guest-checkout change request. In a fixed-order study of 20 participants, 17 recorded at least one additional source-supported item or pair when revisiting the tasks with the prototype; 58 of 69 assessable additional units were judged supported by the source materials. Seven rationales were judged stronger in the second phase, five without a decision-category change. Participants generally found the visualisations helpful, but workload responses varied and some misread visual relationships. The fixed sequence means the changes cannot be attributed specifically to Req-Space; the findings point to keeping relationship meanings and source context clear.

### Source excerpt

arXiv:2611.05437v1 Announce Type: new Abstract: Requirements review involves identifying inconsistencies and assessing change implications across distributed specifications. Motivated by needs raised in industrial project workshops, we investigate Req-Space, an interactive prototype integrating semantic exploration and traceability visualisation to support human-led review. We conducted a fixed-order, two-phase study with 20 participants, including 11 with at least three years of software or IT experience. Participants reviewed a fictional 40-requirement software specification and a guest-checkout change request, first using source documents and then revisiting the same tasks with Req-Space. During the supported review, 17 participants recorded at least one additional source-supported item or pair. Of 69 assessable additional units, 58 (84.1%) were judged supported by the source materials. Seven decision rationales were judged stronger in Phase 2, including five without a change in the decision category. Participants generally found the visualisations helpful, although workload responses were mixed and some misinterpreted visual relationships. The findings suggest that visual support can facilitate requirements exploration and decision justification, provided relationship meanings and source context remain clear. The fixed study sequence prevents attributing the observed changes specifically to Req-Space.

## PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions

DevFeed: [PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions](<https://devfeed.tech/articles/personacodebench-evaluating-coding-agents-in-persona-driven-human-interactive-sessions-118369.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.05739>)

Author: Haixin Wang, Jianheng Hou, Hongyu Shen, Wenzhe Fan, Wei-Chieh Huang, Qianyu Zhu, Weichen Li, Taoran Li, Yuhang Yao, Ruohan Wang, Zhejian Peng, Wanting Jiang, Yifan Chen, Shushu Liang, Haoming Li, Defu

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Human-AI evaluation](<https://devfeed.tech/topics/human-ai-evaluation.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Interactive AI Systems](<https://devfeed.tech/topics/interactive-ai-systems.md>), [ai alignment](<https://devfeed.tech/topics/ai-alignment.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [budget](<https://devfeed.tech/tags/budget.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

PersonaCodeBench evaluates coding agents on both software correctness and fulfillment of explicit user expectations in multi-turn sessions. It converts personas' roles, technical abilities, interaction preferences, and practical constraints into task-specific requirements for implementation, permissions, testing, explanation, and delivery. A runtime controller manages simulated user responses and progressive requirement disclosure, while online evaluation provides feedback. Separate verifiers assess completion and persona fulfillment; a joint pass requires meeting the declared budget and validity conditions as well as both assessment goals. The abstract says the authors evaluated frontier agents and produced a leaderboard, but provides no results or agent rankings.

### Source excerpt

arXiv:2611.05739v1 Announce Type: new Abstract: Coding agents must deliver correct software while respecting users' expertise, preferences, and working conditions. Existing benchmarks increasingly incorporate interaction, yet personalized requirement fulfillment remains underexplored. We introduce PersonaCodeBench, which turns user characteristics into verifiable obligations in persona-driven multi-turn coding sessions. Our persona pool spans roles, technical abilities, interaction preferences, and practical constraints, yielding task-grounded evolved requirements for implementation, permissions, testing, explanation, and delivery. At runtime, a controller governs user simulator responses and requirement disclosure, using online requirement evaluation to provide feedback and advance the interaction. Requirements emerge progressively, with their content, disclosure conditions, and acceptance criteria fixed before evaluation. A completion verifier and a personalization verifier separately assess native correctness and persona fulfillment. Joint pass requires both adherence to the declared budget and compliance with validity conditions. We evaluate all major frontier agents, establish a comprehensive leaderboard, and conduct detailed experimental analyses to validate effectiveness. PersonaCodeBench supports reproducible evaluation of coding agents' ability to meet explicit, personalized user expectations alongside coding objectives.

## Use Cases: The Ideal Bridge Between Requirements and Design?

DevFeed: [Use Cases: The Ideal Bridge Between Requirements and Design?](<https://devfeed.tech/articles/use-cases-the-ideal-bridge-between-requirements-and-design-123010.md>)

Original publisher: [Read original article](<https://ixdf.org/literature/article/uses-cases-diagrams-narratives>)

Published: 2026-11-04T12:00:00Z

Content type: article

Language: en

Sources: [UX Daily - User Experience Daily](<https://devfeed.tech/sources/ux-daily-user-experience-daily.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [User Experience](<https://devfeed.tech/topics/user-experience.md>), [Interaction Design](<https://devfeed.tech/topics/interaction-design.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>)

Tags: [actor](<https://devfeed.tech/tags/actor.md>), [agile](<https://devfeed.tech/tags/agile.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [behaviors](<https://devfeed.tech/tags/behaviors.md>), [booking](<https://devfeed.tech/tags/booking.md>), [calendar](<https://devfeed.tech/tags/calendar.md>), [cc-by-sa](<https://devfeed.tech/tags/cc-by-sa.md>), [components](<https://devfeed.tech/tags/components.md>), [design](<https://devfeed.tech/tags/design.md>), [designers](<https://devfeed.tech/tags/designers.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development](<https://devfeed.tech/tags/development.md>), [diagram](<https://devfeed.tech/tags/diagram.md>), [email](<https://devfeed.tech/tags/email.md>), [exceptions](<https://devfeed.tech/tags/exceptions.md>), [flight](<https://devfeed.tech/tags/flight.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [stories](<https://devfeed.tech/tags/stories.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>), [user-experience](<https://devfeed.tech/tags/user-experience.md>)

### AI overview

Use cases describe system behavior from the perspective of the people and other systems interacting with it, using diagrams for an overview and narratives for interaction details. Diagrams show actors and associated use cases but omit sequence; narratives can specify goals, preconditions, a basic flow, alternatives and postconditions, though no standard format is given. Capture exceptions and edge cases alongside the typical flow. Match detail to the design stage: early stories should avoid interface implementation choices that can constrain later design; add those details when appropriate.

### Source excerpt

Imagine trying to describe everything your product needs to do, without getting lost in technical detail or endless feature lists. That's the problem Ivar Jacobson set out to solve in the 1980s when he introduced use cases. Instead of worrying about how a system worked internally, he described it from the outside, as if it were a "black box," focusing on what it does for the people and systems that interact with it. This enabled developers to capture requirements more clearly and consistently, paving the way for the stories of use we rely on today.In this video, William Hudson, User Experience Strategist and Founder of Syntagm Ltd, introduces use cases and explains how Ivar Jacobson created...

## Semantic Interoperability in Federated Digital Twin Systems: A Systematic Review Through the Levels of Conceptual Interoperability Model

DevFeed: [Semantic Interoperability in Federated Digital Twin Systems: A Systematic Review Through the Levels of Conceptual Interoperability Model](<https://devfeed.tech/articles/semantic-interoperability-in-federated-digital-twin-systems-a-systematic-review-through-the-levels-of-conceptual-interoperability-model-113518.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02125>)

Author: Manonmani Sekar, Nasim Nezamoddini

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Data Space](<https://devfeed.tech/topics/data-space.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [digital-twin](<https://devfeed.tech/tags/digital-twin.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [federated](<https://devfeed.tech/tags/federated.md>), [interoperability](<https://devfeed.tech/tags/interoperability.md>), [review](<https://devfeed.tech/tags/review.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

The review found no published system among its 32 included studies that detects and repairs broken mappings between independently owned digital twins while they operate. It screened 5,833 records and examined 119 full texts. Cross-company matching was studied without checking whether a match remained valid, while detection and repair of changed meanings appeared only within single-company systems. The authors distill this gap into six requirements for systems claiming run-time semantic interoperability, illustrated with a running example.

### Source excerpt

arXiv:2611.02125v1 Announce Type: new Abstract: When two companies connect their digital twins, software models of their plants kept up to date with live data, each twin must translate the other's data into its own terms, and that translation rule, called a mapping, can stop being correct when one company changes the meaning of its data without telling the other. This PRISMA 2020 systematic review screened 5,833 records and read 119 full texts to determine whether any published system detects such a broken mapping and repairs it while the twins operate. In all 32 included studies the mapping is fixed before operation, and the two ingredients of run-time repair appear only separately: cross-company matching without any check that the match still holds, and detection and repair of changed meaning within a single company. The review turns this gap into six requirements, each illustrated on one running example, that a system claiming run-time semantic interoperability between independently owned twins should meet.

## Beyond Surface Metrics: Multi-Condition Requirements in Enterprise Maintenance and AI Coding Benchmarks

DevFeed: [Beyond Surface Metrics: Multi-Condition Requirements in Enterprise Maintenance and AI Coding Benchmarks](<https://devfeed.tech/articles/beyond-surface-metrics-multi-condition-requirements-in-enterprise-maintenance-and-ai-coding-benchmarks-113536.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03162>)

Author: Heeyong Eun (KPMG Korea)

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>)

Tags: [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [condition](<https://devfeed.tech/tags/condition.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [swe-bench](<https://devfeed.tech/tags/swe-bench.md>), [swe-bench-pro](<https://devfeed.tech/tags/swe-bench-pro.md>)

### AI overview

A fixed 18-criterion analysis finds that benchmark tasks and Apache Fineract maintenance issues can have very different fulfillment-condition sets despite similar surface task profiles. Among 1,177 benchmark tasks matched on issue classification, modified-file count, and code churn, mean Jaccard distance was 0.8138, and 57.4% had disjoint condition sets. Condition breadth alone did not explain the difference: SWE-bench Pro averaged 2.47 conditions per task versus Fineract's 1.78. Temporal and numerical conditions co-occurred more in Fineract (φ=+0.430) than in the pooled benchmarks (−0.013); numerical conditions appeared in 48.85% of temporally tagged Fineract cases versus 5.81% of benchmark cases. The study documents 16 directional requirement relationships in Fineract and examines four benchmark cases, but those examples do not measure benchmark-wide oracle omissions. It recommends reporting condition breadth, co-occurrence, and directional relationships separately. Comparisons are descriptive, may reflect domain differences, and establish neither causality nor production failure rates.

### Source excerpt

arXiv:2611.03162v1 Announce Type: new Abstract: Repository-level AI coding benchmarks measure task success but do not directly capture the conditions required for software maintenance completion. We study multi-condition fulfillment, where a maintenance task must satisfy multiple operational conditions, sometimes with directional dependencies. Using a fixed 18-criterion taxonomy, we analyze 2,925 Apache Fineract issues and 944 tasks from SWE-bench Pro, SWE-PolyBench Java, and SWE-EVO. We examine condition breadth, corpus-level co-occurrence, and source-grounded directional requirement relationships. Among 1,177 benchmark task pairs matched on issue classification, modified-file count, and code churn, the mean fulfillment-set Jaccard distance is 0.8138, and 57.4% have disjoint condition sets. Condition count alone does not explain this contrast: SWE-bench Pro averages 2.47 conditions per task, versus 1.78 for Fineract. Temporal (B4) and numerical (B2) conditions have a phi coefficient of +0.430 in Fineract versus -0.013 in the pooled benchmark corpus. Among temporally tagged tasks, numerical conditions are also specified in 48.85% (254/520) of Fineract cases versus 5.81% (5/86) of benchmark cases. We document 16 directional relationships in Fineract requirements involving time, calculation, and state preservation, and inspect four benchmark cases to illustrate how relevant conditions appear in evaluation assertions. These examples do not quantify benchmark-wide oracle omissions. The results show that similar surface task profiles can mask substantially different fulfillment-condition sets. We recommend reporting condition breadth, co-occurrence, and directional relationships separately. The corpus comparisons are descriptive and may reflect domain differences; they do not establish causality or production failure rates.

## Supporting Viewpoint Coordination for Compliance by Design with an Artifact Model for Regulatory Requirements Engineering

DevFeed: [Supporting Viewpoint Coordination for Compliance by Design with an Artifact Model for Regulatory Requirements Engineering](<https://devfeed.tech/articles/supporting-viewpoint-coordination-for-compliance-by-design-with-an-artifact-model-for-regulatory-requirements-engineering-113543.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.03631>)

Author: Oleksandr Kosenkov, Davide Fucci, Michael Unterkalmsteiner, Daniel Mendez

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>)

Tags: [bridging](<https://devfeed.tech/tags/bridging.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [design](<https://devfeed.tech/tags/design.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [experts](<https://devfeed.tech/tags/experts.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [legal](<https://devfeed.tech/tags/legal.md>), [model](<https://devfeed.tech/tags/model.md>), [processes](<https://devfeed.tech/tags/processes.md>), [quality](<https://devfeed.tech/tags/quality.md>), [regulatory](<https://devfeed.tech/tags/regulatory.md>), [regulatory-compliance](<https://devfeed.tech/tags/regulatory-compliance.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [requirements-engineering](<https://devfeed.tech/tags/requirements-engineering.md>), [research](<https://devfeed.tech/tags/research.md>), [software](<https://devfeed.tech/tags/software.md>), [software-design](<https://devfeed.tech/tags/software-design.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The authors propose AM4RRE, an artifact model implemented through templates to coordinate legal and software engineering viewpoints when specifying regulatory requirements for compliance by design. In an evaluation, most of 37 practitioners rated it positively for coordination and requirements quality. A quasi-experiment involving 34 practitioners in 10 groups found template-guided coordination was associated with shorter average total specification time when used first, and higher requirements quality in most groups where the approach varied. The results suggest potential benefits, but the supplied abstract does not establish broad effects beyond these evaluations.

### Source excerpt

arXiv:2611.03631v1 Announce Type: new Abstract: Regulatory compliance has become an essential software requirement Legal demands for compliance by design CbD call for requirements engineering RE approaches that derive requirements and support compliance implementation in subsequent software engineering SE processes such as software design The complexity of the legal knowledge demanded in regulatory RE makes it important to involve legal experts and ensure the relevant specifications are valid and usable for them Regulatory requirements must support compliance implementation in software design However there is a lack of approaches bridging legal and SE viewpoints and interaction challenges between the two persist To address engineeringlegal coordination in specification of regulatory requirements we propose the Artifact Model for Regulatory Requirements Engineering AM4RRE operationalized through templates AM4RRE was positively evaluated by most of the 37 practitioners for coordination in regulatory RE and for supporting requirements quality Results from a quasiexperiment with 34 of them in 10 groups indicated that templateguided coordination was associated with on average shorter total specification time when executed first and higher requirements quality in most groups in which it varied Existing RE research and practice provide little attention and support for viewpoint coordination in regulatory RE for CbD Artifactoriented approaches such as AM4RRE have the potential to guide coordination in RE for better RE results and contribute to concretizing the role and contribution of RE to CbD

## When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

DevFeed: [When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications](<https://devfeed.tech/articles/when-requirements-interact-scaling-long-horizon-coding-via-interdependent-specifications-107407.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.40256>)

Author: Yishuo Cai, Minzheng Wang, Liang Zhao, Linghao Zhang, Lei Li, Shicheng Li, Xu Sun, Fuli Luo

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [Specifications](<https://devfeed.tech/topics/specifications.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [applying](<https://devfeed.tech/tags/applying.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audits](<https://devfeed.tech/tags/audits.md>), [base](<https://devfeed.tech/tags/base.md>), [bench](<https://devfeed.tech/tags/bench.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bridge](<https://devfeed.tech/tags/bridge.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [complex](<https://devfeed.tech/tags/complex.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [specifications](<https://devfeed.tech/tags/specifications.md>)

### AI overview

CodeSpecWeave targets long-horizon coding tasks where requirements such as interface compatibility and error handling must be met without breaking dependencies. Its pipeline starts from real developer seeds: a synthesis agent builds coupled requirements and executable tests, then a review agent audits solution trajectories from multiple models to check test reliability. The authors report 4,670 training tasks across 2,865 repositories; reinforcement learning on these tasks improved DeepSWE-v1.1 over its base model and largely outperformed existing baselines. Their benchmark contains 100 tasks and 1,044 specifications, and distinguishes frontier models while indicating substantial remaining difficulty with interdependent constraints.

### Source excerpt

arXiv:2610.40256v1 Announce Type: new Abstract: To succeed in real-world long-horizon software development, coding agents must satisfy multi-dimensional task specifications, such as interface compatibility and error handling, and do so without breaking existing dependencies. However, current works lack specification in both quantity and diversity, often emphasizing primary goals while ignoring complex constraints. Synthesizing tasks to bridge this gap presents two challenges: naively adding specifications risks reducing tasks to trivial checklists rather than compelling joint reasoning, and verifying these subtle interactions risks overlooking hidden flaws or rejecting valid alternatives. To address these challenges, we introduce CodeSpecWeave, a framework for synthesizing tasks with rich, interdependent specifications. Grounded in real developer seeds, a synthesis agent iteratively develops both coupled task requirements and executable tests, while a review agent audits solution trajectories from multiple models to guarantee test reliability. Using this pipeline, we construct 4,670 training tasks across 2,865 repositories. Applying Reinforcement learning on these tasks significantly improves performance over the base model on DeepSWE-v1.1, largely outperforming existing baselines. Furthermore, we curate CodeSpecWeave-Bench, a rigorous benchmark comprising 100 tasks and 1,044 specifications, which clearly separates frontier models and reveals significant headroom in handling interdependent engineering constraints.

## Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements

DevFeed: [Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements](<https://devfeed.tech/articles/benchmarking-llm-agents-for-behaviorally-adequate-test-generation-from-software-requirements-103159.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36584>)

Author: Binhang Qi, Yiming Liu, Yun Lin, Yangjie Zhou, Hailong Sun, Jin Song Dong

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [mutation-testing](<https://devfeed.tech/topics/mutation-testing.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Behavior-driven development](<https://devfeed.tech/topics/bdd.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [bdd](<https://devfeed.tech/tags/bdd.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [codex](<https://devfeed.tech/tags/codex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [execution](<https://devfeed.tech/tags/execution.md>), [file](<https://devfeed.tech/tags/file.md>), [frameworks](<https://devfeed.tech/tags/frameworks.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [software](<https://devfeed.tech/tags/software.md>), [test](<https://devfeed.tech/tags/test.md>)

### AI overview

Req2Test-Bench evaluates whether agents can generate tests from Gherkin requirements and target interfaces when behavior implementations are withheld. It contains 5,086 execution-validated instances from eight open-source projects across five languages and four BDD frameworks. Adequacy is measured strictly by kill-completeness: a generated test must kill every mutant killed by the developer-written test. Across eight agent-model-reasoning configurations, the best, Codex with DeepSeek-V4.1-Flash, generated passing tests for 82.8% of instances, but only 33.8% were behaviorally adequate. The authors report sharply diminishing adequacy gains as agent scale and generation cost increase, and identify ambiguous setup and implicit expected outcomes in underspecified requirements as sources of information gaps. They suggest requirement-grounded harnesses to steer agent nondeterminism as a possible improvement.

### Source excerpt

arXiv:2610.36584v1 Announce Type: cross Abstract: As large language model agents increasingly compile natural-language requirements into repository-level code, requirement-to-test generation grows in importance to provide validation constraints (or harness) to guide code generation. Yet it remains unclear whether current agents can generate tests that validate the required behavior when the implementation of that behavior is withheld. Existing test-generation benchmarks mostly focus on white-box testing, whereas the requirement--test-related study usually requires evaluation on semantic alignment between the given documents and the generated tests. We introduce Req2Test-Bench, a benchmark containing 5,086 execution-validated instances recovered from developer-authored behavior-driven development (BDD) artifacts in 8 open-source projects, spanning 5 programming languages and 4 BDD frameworks. Each instance pairs a natural-language requirement in Gherkin with its developer-written Test Implementation. Given the requirement, target interfaces of the required behavior, an agent must generate a complete, potentially multi-file Test Implementation. Evaluation of 8 agent--model--reasoning configurations reveals a substantial gap between execution success and behavioral adequacy, which is measured strictly as kill-completeness: a kill-complete test kills every mutant that the ground-truth test kills. The best-performing configuration, Codex with DeepSeek-V4.1-Flash, produces passing tests for 82.8% of instances, yet only 33.8% are behaviorally adequate. We find that (1) scaling up agents yields sharply diminishing returns in behavioral adequacy relative to generation cost; (2) under-specified requirements cause the information gap, including ambiguous setup and implicit expected outcomes; and (3) requirement-grounded harnesses that steer agent non-determinism offer a promising direction for improvement.

## DRILS: Dependency-based Requirement Change Impact Analysis Using LLMs

DevFeed: [DRILS: Dependency-based Requirement Change Impact Analysis Using LLMs](<https://devfeed.tech/articles/drils-dependency-based-requirement-change-impact-analysis-using-llms-101756.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33920>)

Author: Romina Etezadi, Ikram Darif, Lionel Briand, Ramesh S, Parkish Peranandam

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Requirements](<https://devfeed.tech/topics/requirements.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agent-architecture](<https://devfeed.tech/tags/agent-architecture.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [change](<https://devfeed.tech/tags/change.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [false-positives](<https://devfeed.tech/tags/false-positives.md>), [impact](<https://devfeed.tech/tags/impact.md>), [llms](<https://devfeed.tech/tags/llms.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [performance](<https://devfeed.tech/tags/performance.md>), [precision](<https://devfeed.tech/tags/precision.md>), [rag](<https://devfeed.tech/tags/rag.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

DRILS combines a multi-agent process that generates candidate requirement-impact sets with an LLM judge that promotes diversity in selection. It adds focused domain context through RE-RAG and uses a requirement dependency graph as another knowledge source. Across three manually curated datasets, the authors report average recall of 87.1%, precision of 76.3%, and F1 of 81% at lower cost than state-of-the-art baselines; precision gains over the closest baseline were 41.1%, 83.4%, and 149.8% across the datasets. The abstract also reports three annotated CIA datasets contributed for future research.

### Source excerpt

arXiv:2610.33920v1 Announce Type: new Abstract: Change is inevitable in software systems, where requirements must continuously adapt to evolving stakeholder needs, regulations, and project scopes. Managing such changes is a fundamental software engineering challenge, as manually identifying the impact of a change request, given high requirements volume, Natural Language (NL) complexity, and intricate interdependencies, is error-prone and time-consuming. Large Language Models (LLMs) offer promising solutions for requirements change impact analysis (CIA), yet their effectiveness when enhanced with advanced techniques remains underexplored. We present DRILS, an LLM-based agentic framework for requirements Change Impact Analysis, employing a multi-agent architecture to generate candidate impact sets, with an LLM-as-a-judge promoting diversity during selection. DRILS features two key components: RE-RAG, a carefully engineered RAG technique providing focused domain context, and a requirement dependency graph (RDG) as an additional knowledge source. Evaluation across three manually curated datasets demonstrates superior performance over state-of-the-art baselines, achieving an average recall of 87.1%, precision of 76.3%, and F1 score of 81% at a lower cost. Precision gains are particularly significant, 41.1%, 83.4%, and 149.8% over the closest baseline per dataset, as higher precision directly reduces false positives and manual validation effort. We also contribute three annotated CIA datasets to support future research.

## FeatureLoop: Benchmarking Coding Agents under Evolving Requirements

DevFeed: [FeatureLoop: Benchmarking Coding Agents under Evolving Requirements](<https://devfeed.tech/articles/featureloop-benchmarking-coding-agents-under-evolving-requirements-101808.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.35488>)

Author: Jia Feng, Alyssa Wu, Cuiyun Gao, Yunlong Wang, Songyuanyi Lu, Zhichao Hu

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [Application Development](<https://devfeed.tech/topics/application-development.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [development](<https://devfeed.tech/tags/development.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [evolution](<https://devfeed.tech/tags/evolution.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [frontier-models](<https://devfeed.tech/tags/frontier-models.md>), [functionality](<https://devfeed.tech/tags/functionality.md>), [languages](<https://devfeed.tech/tags/languages.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [programming](<https://devfeed.tech/tags/programming.md>), [programming-languages](<https://devfeed.tech/tags/programming-languages.md>), [recover](<https://devfeed.tech/tags/recover.md>), [repair](<https://devfeed.tech/tags/repair.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [requirements](<https://devfeed.tech/tags/requirements.md>)

### AI overview

FeatureLoop evaluates coding agents on 61 human-reviewed tasks from 34 repositories, tracking work in persistent workspaces as requirements evolve and failures prompt corrective feedback. Its cumulative executable checks measure new behavior, repair, and preservation of existing functionality. Across 12 frontier models, the strongest completed 72.1% of tasks with both feedback types, but only 15.4% of failed stages recovered within two corrective revisions across models. The abstract also reports incomplete repairs, regressions, and model differences in feedback use and token efficiency.

### Source excerpt

arXiv:2610.35488v1 Announce Type: new Abstract: Software development with coding agents often begins with a rough request that users refine after trying the implementation. Final correctness alone does not capture the repeated guidance this process requires. We introduce FeatureLoop, a benchmark of 61 human-reviewed tasks from 34 repositories across five primary programming languages and seven software forms. Each task follows one development goal in a persistent workspace through evolution feedback, which adds or clarifies requirements, and completion feedback, which reports failures of stated requirements. Cumulative executable checks track new behavior, repair, and preservation of earlier functionality. We evaluate 12 frontier models and find that the strongest completes 72.1% of tasks with both feedback types. Across models, however, only 15.4% of observed failed stages recover within two corrective revisions. Further analysis reveals incomplete repairs, regressions, and model-specific differences in feedback use and token efficiency, identifying obstacles to reliable, low-intervention development.

## Multimodal Requirements Traceability Link Recovery in Industrial Settings

DevFeed: [Multimodal Requirements Traceability Link Recovery in Industrial Settings](<https://devfeed.tech/articles/multimodal-requirements-traceability-link-recovery-in-industrial-settings-101775.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.34503>)

Author: Haoming Huang, Shinpei Hayashi, Kazuya Kohata, Myeongki Kim, Yuki Kurihara

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [vlm](<https://devfeed.tech/topics/vlm.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>)

Tags: [confidence](<https://devfeed.tech/tags/confidence.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [image](<https://devfeed.tech/tags/image.md>), [images](<https://devfeed.tech/tags/images.md>), [industrial](<https://devfeed.tech/tags/industrial.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [links](<https://devfeed.tech/tags/links.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [rag](<https://devfeed.tech/tags/rag.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [requirements](<https://devfeed.tech/tags/requirements.md>), [requirements-traceability](<https://devfeed.tech/tags/requirements-traceability.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [retrieval-augmented-generation-rag](<https://devfeed.tech/tags/retrieval-augmented-generation-rag.md>), [traceability](<https://devfeed.tech/tags/traceability.md>), [vision-language-model](<https://devfeed.tech/tags/vision-language-model.md>)

### AI overview

The RAG-based approach retrieves text and image candidates separately, classifies candidate pairs with a vision-language model, and filters predicted links by verbalized confidence. Across three industrial requirement sets, it achieved F1 0.310 versus 0.114 for a replication of the Hey et al. baseline, recovered links across all four modality combinations, and improved industrial text-only F1 while maintaining similar performance on six public text-only datasets. Recovery was limited by failures to retrieve related text requirements for image queries. Confidence filtering changes precision and recall, removing false positives as well as some correct links; the study identifies cross-modal retrieval as a priority for further optimization.

### Source excerpt

arXiv:2610.34503v1 Announce Type: new Abstract: Requirements traceability links support activities such as change-impact analysis, coverage checking, and validation. Industrial requirements can include traceable images, which text-only approaches cannot process directly. For a fixed classifier configuration, binary decisions alone offer no direct way to adjust the balance between missed and incorrect links. We extend a retrieval-augmented generation (RAG) approach for inter-requirements traceability link recovery (TLR). Our extension retrieves text and image candidates separately, classifies each retrieved pair with a vision-language model, and filters the predicted links by verbalized confidence. We evaluate our approach on three non-overlapping industrial requirement sets and six public text-only datasets. On the industrial test sets, our approach achieves an F1 score of 0.310, compared with 0.114 for our replication of the baseline approach by Hey et al. Our approach recovers links in all four modality combinations while improving text-only F1 on the industrial data and maintaining similar performance on the public datasets, but recovery remains limited by failures to retrieve related text requirements for image queries. Confidence filtering produces link sets with different precision and recall, removing false positives and some correctly recovered links from the unfiltered link set. This study provides industrial evidence on the potential and limitations of a current RAG-based TLR approach for multimodal requirements and identifies cross-modal retrieval as the component to prioritize in further optimization.

[Next page](<https://devfeed.tech/topics/requirements.md?cursor=WyIyMDI2LTEwLTI3VDA0OjAwOjAwKzAwOjAwIiwgIjA1YWVlMmNmLTRhODktNDEzZC05MmVmLWQ4YzM1OWY5OWQ4NCJd>)