Requirements Engineering

Follow this topic Ask about this topic

Latest papers 50

6 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

All topics

Fidelity Probes for Specification--Code Alignment
May 17, 2026Ferhat Erata, Hao Zhou, Luke HuanRequirements Engineering
AWS Agentic AI
Neurosymbolic Auditing of Natural-Language Software Requirements
May 13, 2026Bethel Hall, William EiersRequirements Engineering Formal Verification
Stevens Institute of Technology
Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent
May 13, 2026Hao Wang, Ligong Han, Kai Xu +1Requirements Engineering Software Engineering Agents
Red Hat AI Innovation · MIT-IBM Watson AI Lab · IBM Core AI
Read, Extract, Classify: A Tool for Smarter Requirements Engineering
May 11, 2026Paheli Bhattacharya, Manojit Chakraborty, Santhosh Kumar Arumugam +1Requirements Engineering Document Information Extraction
Bosch Research and Technology Centre, Bangalore, India
Neuro-Symbolic Agents for Hallucination-Free Requirements Reuse
May 2, 2026Ahmed F. IbrahimMulti-Agent LLM Systems Requirements Engineering
Western University London, Canada
ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation
Apr 25, 2026Haowei Cheng, Milhan Kim, Chong Liu +6Requirements Engineering Multi-Agent Negotiation
Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan · College of Architecture and Urban Planning, Tongji University, Shanghai, China · Advanced Institute of So-Go-Chi (Convergence Knowledge) Informatics, Tohoku University, Miyagi, Japan +1
Evaluating LLM-Based Goal Extraction in Requirements Engineering: Prompting Strategies and Their Limitations
Apr 24, 2026Anna Arnaudo, Riccardo Coppola, Maurizio Morisio +4Requirements Engineering LLM Prompting
Department of Control and Computer Engineering, Politecnico di Torino · Politecnico di Torino
Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitation
Apr 23, 2026Shihai Wang, Tao ChenRequirements Engineering Preference Learning
School of Computer Science and Engineering, UESTC, Chengdu, China · IDEAS Lab, University of Birmingham, Birmingham, UK
Structural Quality Gaps in Practitioner AI Governance Prompts: An Empirical Study Using a Five-Principle Evaluation Framework
Apr 22, 2026Christo ZietsmanRequirements Engineering AI Agent Governance
Nuphirho Research
Persona-Based Requirements Engineering for Explainable Multi-Agent Educational Systems: A Scenario Simulator for Clinical Reasoning Training
Apr 19, 2026Weibing Zheng, Laurah Turner, Jess Kropczynski +3Requirements Engineering Explainable Artificial Intelligence
School of Information Technology · College of Medicine
AI-Assisted Requirements Engineering: An Empirical Evaluation Relative to Expert Judgment
Apr 16, 2026Oz Levy, Ilya Dikman, Natan Levy +1Requirements Engineering Human-in-the-Loop Evaluation
Faculty of Industrial Engineering and Technology Management, Holon Institute of Technology (HIT) Holon, Israel · School of Computer Science and Engineering Hebrew University Jerusalem (HUJI) Jerusalem, Israel
IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering
Apr 1, 2026Elliott Watkiss-Leek, Reham Alharbi, Harry Rostron +6Requirements Engineering
School of Computer Science and Informatics, University of Liverpool, Brownlow Hill, Liverpool, L69 7ZX, UK · College of Computer Science and Engineering, Taibah University, Saudi Arabia · Unilever Plc., Materials Innovation Factory, University of Liverpool, 51 Oxford Street, Liverpool, L7 3NY, UK
Towards Explainable Stakeholder-Aware Requirements Prioritisation in Aged-Care Digital Health
Mar 31, 2026Yuqing Xiao, John Grundy, Anuradha Madugalla +1Requirements Engineering Healthcare
Monash University, Melbourne, Victoria, Australia · Deakin University, Melbourne, Victoria, Australia
From Reviews to Requirements: Can LLMs Generate Human-Like User Stories?
Mar 30, 2026Shadman Sakib, Oishy Fatema Akhand, Tasnia Tasneem +1Requirements Engineering Text Generation
Department of Computer Science and Engineering, Islamic University of Technology (IUT), Gazipur, Bangladesh
ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains
Mar 24, 2026Muhammad Khalid, Manuel Oriol, Yilmaz UygunRequirements Engineering Automated Software Engineering
Constructor University Bremen, 28759 Bremen, Germany
An Industrial-Scale Retrieval-Augmented Generation Framework for Requirements Engineering: Empirical Evaluation with Automotive Manufacturing Data
Mar 20, 2026Muhammad Khalid, Yilmaz UygunRequirements Engineering RAG Evaluation
Constructor University Bremen, Bremen, Germany
From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems
Feb 28, 2026Yijun YuSoftware Engineering Requirements Engineering
The Open University, Milton Keynes, UK
Automating the Detection of Requirement Dependencies Using Large Language Models
Feb 25, 2026Ikram Darif, Feifei Niu, Manel Abdellatif +3Requirements Engineering
University of Ottawa, Ottawa, Canada. · École de technologie supérieure, Montreal, Canada. · Research Ireland Lero Centre for Software Research, University of Limerick, Ireland. +1
Workflow-Level Design Principles for Trustworthy GenAI in Automotive System Engineering
Feb 23, 2026Chih-Hong Cheng, Brian Hsuan-Cheng Liao, Adam Molin +1LLM Safety Requirements Engineering
Carl von Ossietzky University of Oldenburg, Oldenburg, Germany · DENSO AUTOMOTIVE Deutschland Germany, Eching, Germany
Exploring LLMs for User Story Extraction from Mockups
Feb 19, 2026Diego Firmenich, Leandro Antonelli, Bruno Pazos +2Requirements Engineering Text Generation
Departamento de Informática, Facultad de Ingeniería, Universidad Nacional de la Patagonia, Argentina · LIFIA, Facultad de Informática, Universidad Nacional de La Plata, Argentina · CAETI, Facultad de Tecnología Informática - Universidad Abierta Interamericana +3

May 17, 2026J/K move · Enter open · S save

Fidelity Probes for Specification--Code Alignment

Ferhat Erata, Hao Zhou, Luke Huan

AWS Agentic AI

Requirements Engineering

Open paper AskPDF arXiv

We introduce fidelity probes: natural-language questions generated from a reference artifact with code-derived ground-truth answers, answered from a candidate specification. The fraction of agreeing probes, which we call the fidelity, decomposes into contradiction and coverage-gap rates that drive targeted spec edits to convergence. On a 15-program, roughly 12k-line COBOL benchmark (AWS CardDemo), we raise frozen-test specification fidelity from 0.63 to 0.94 over eight iterations, with the plateau location predicted by a two-state Markov fixed point

F^\dagger

from just four iterations of rate data. Probes come from an LLM reading the code or from a static-analysis pipeline over its control-flow, data-flow, and system-dependence graphs, with a tunable mixture. A probe-resampling protocol with a frozen held-out set gives a Hoeffding-bounded overfitting discriminant; our measured train/test gap stays more than an order of magnitude below this envelope. Three graph-grounded mixtures lift fidelity by +16 to +30 points; cross-distribution evaluation shows the LLM and symbolic channels are empirically complementary. A cross-family generator sweep on five independent LLM lineages (Anthropic, DeepSeek, Google, Alibaba, OpenAI) confirms the convergence behaviour is not tied to any single model family: three of five non-Claude generators produce trajectories consistent with the Markov fixed-point prediction, and the frozen-test protocol actively falsifies the two generators whose probe distributions drift across iterations. The method applies to any pair of artifacts that are supposed to describe the same behaviour.