Requirements Engineering

Latest papers 50

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

Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
Oct 13, 2026Kaiming Liu, Yuxuan Liu, Jinrui Ju +4LLM Agent Evaluation Software Engineering Agents
College of AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China
FDE-Bench: Evaluating End-to-End Delivery from Underspecified Real-World Business Requests
Oct 10, 2026Huaiming Li, Can Huang, Chufan Wu +18LLM Agent Evaluation AI Agent Benchmarks
FM Agent Team, Baidu AI Cloud · Beijing University of Posts and Telecommunications · The Chinese University of Hong Kong +4
GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks
Oct 8, 2026Amirhossein Vahdat, Thierry Badard, Luc LamontagneLLM Evaluation Geospatial Reasoning
Département des Sciences Géomatiques, Université Laval, QC, Canada · Département d’informatique et de génie logiciel, Université Laval, QC, Canada
Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking
Oct 7, 2026Yongjian Tang, Linhan Li, Thomas RunklerRequirements Engineering Software Engineering Agents
Siemens AG (RPD) Germany · Technical University of Munich Munich, Germany · Siemens AG Germany
Toward AI-Augmented Cooperative Engineering Workflows: Requirements and Architecture the European Rover Challenge
Sep 25, 2026Ahmed R. Sadik, Frank Joublin, Mariusz Bujny +2Human-AI Collaboration Requirements Engineering
Honda Research Institute Europe, Offenbach, 63073, Germany · NUMETO, Katowice, Poland · Honda Research Institute USA, Ohio, USA
From Code to Requirements: Agentic Reverse Engineering of Business Rules at Enterprise Scale
Sep 19, 2026Garima Agrawal, Prasun Das, Priyanka L +5Requirements Engineering Software Reverse Engineering
Cognizant, Plano, Texas, USA
Relationally Guided Use Case Modeling with LLMs
Sep 16, 2026Guangyu Wang, Bangqi Li, Ji Wu +1Requirements Engineering
School of Computer Science and Engineering, Beihang University, Beijing, 100191, Beijing, China · Xi’an Aeronautics Computing Technique Research Institute, AVIC, Xi’an, 710065, Shaanxi, China · Engineering Research Center of Integration and Application of Digital Learning Technology, Ministry of Education, China
MAIA: Multi-Agent Intent Articulation for Requirement Discovery in Art Commissions
Sep 10, 2026Yu-Chao Wang, Yanhong Lu, Yingjie Victor Chen +1Requirements Engineering Human-in-the-Loop AI
School of Applied and Creative Computing Purdue University West Lafayette, Indiana, USA
WiseSpec: Requirements-Driven Agents for Code Generation
Sep 1, 2026Zhao TianRequirements Engineering Software Engineering Agents
School of Computer Software, Tianjin University Tianjin, China
Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark
Aug 19, 2026Oleg Grynets, Dmytro Kostetskyi, Vasyl LyashkevychSoftware Engineering Benchmarks Requirements Engineering
EPAM Systems McLean, Virginia, USA · EPAM Systems Lviv, Ukraine
A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Generation for Coding Agents
Aug 10, 2026Xin Zhou, Chun Yong Chong, Kisub Kim +11Requirements Engineering AI Coding Agents
Singapore Management University, Singapore · Monash University Malaysia, Malaysia · Daegu Gyeongbuk Institute of Science and Technology (DGIST), Republic of Korea +5
IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical Requirements
Aug 9, 2026Shiva AhirRequirements Engineering Few-Shot Prompting
Department of Electrical & Computer Engineering Stony Brook University New York, United States of America
AI-assisted Script Management for Requirements Elicitation Interviews
Aug 3, 2026Anmol Singhal, Paulo Carvalho, Travis BreauxRequirements Engineering Human-in-the-Loop AI
Carnegie Mellon University, Pittsburgh, USA
Integrating AI into Requirements Quality Learning in Software Engineering Education: A TPACK-Guided Empirical Study
Jul 30, 2026Hansika Ekanayake Mudiyanselage, Rohan Jai Dharmaraj, Malik Abdul Sami +1Requirements Engineering Computer Science Education
Software Engineering Research Center (TASE), Tampere University, Finland
SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch
Jul 29, 2026Yihao Chen, Shi Chang, Feng Lin +4Requirements Engineering LLM Agent Orchestration
2Queen’s University · 1Huawei Canada · 4Concordia University +1
Model-Driven Requirements Configuration with Three-Valued Uncertainty Scoring
Jul 28, 2026Ahmed IbrahimLogical Reasoning Requirements Engineering
aWestern University, London, Canada
From Dyad to Triad: Eliciting XAI Requirements in Stroke Rehabilitation
Jul 28, 2026Param Rajpura, Yogesh Kumar MeenaRequirements Engineering Explainable Artificial Intelligence
Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, India
How Well Can AI Generate Backlogs from App Mockups?
Jul 24, 2026Andrea Lezcano Airaldi, Lourdes Romera, Walid MaalejRequirements Engineering Prompt Engineering
Department of Informatics · Hasso Plattner Institute
Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications
Jul 20, 2026Mansur Arief, Nur Ahmad Khatim, Ali Akarma +1Requirements Engineering Automated Software Testing
Industrial and Systems Engineering, King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia · Division of Information Science, Nara Institute of Science and Technology (NAIST), Japan · Faculty of Computer and Information Systems Islamic University of Madinah Madinah, Saudi Arabia +1
ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents
Jul 18, 2026Ragib Shahariar Ayon, Rayed Fahmi, Sumon Biswas +1Requirements Engineering Synthetic Data Generation
Texas State University, San Marcos, TX, USA · Case Western Reserve University, Cleveland, OH, USA
Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
Jul 13, 2026Umm-e- Habiba, Lucas Mauser, Jonas Fritzsch +2Requirements Engineering Explainable Artificial Intelligence
TUM School of CIT, Technical University of Munich, Heilbronn, Germany · Daimler Truck AG, Leinfelden-Echterdingen, Germany · Institute of Software Engineering, University of Stuttgart, Stuttgart, Germany +1
From Regulation to Requirements: An Automated Requirement Derivation and Explanation Pipeline
Jul 5, 2026Pavithra PM Nair, Preethu Rose AnishRequirements Engineering Legal Document Analysis
Tata Consultancy Services
A Retrieval-Augmented Framework for Detecting and Resolving Pragmatic Ambiguities in Natural Language Requirements
Jul 5, 2026Pavithra PM Nair, Preethu Rose AnishRequirements Engineering Pragmatic Reasoning in Language Models
Tata Consultancy Services Pune, India
From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems
Jun 30, 2026Amel Bennaceur, Gopi Krishnan Rajbahadur, Prince Mercy +2Requirements Engineering
The Open University, United Kingdom · City St George’s, United Kingdom · Queen’s University, Canada +1
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
Jun 23, 2026Ali Pourghasemi Fatideh, Wilder Baldwin, Maria Dhakal +2Requirements Engineering LLM Evaluation
University of Maine · University of Notre Dame
Cluster-Aware Dual-Level Test Specification Generation for Large-Scale Automotive Software Requirements
Jun 15, 2026Hazem Ayman, Menna Sedik, Kareem Mostafa +3Requirements Engineering Automated Software Testing
CairoMotive Cairo, Egypt
Developing a UXR Point of View for Cognitive Accessibility in Mobile Learning with Generative AI
May 29, 2026Fatima Ahmad Muazu, Festus Adedoyin, Huseyin Dogan +3Requirements Engineering Educational Technology
School of Computing and Engineering, Bournemouth University Poole, UK
SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM Agents
May 28, 2026Grant Hamblin, Kevin Song, Zhanda Zhu +4Requirements Engineering Software Engineering Agents
University of Toronto · Toronto, Ontario, Canada · University of Waterloo +3
EdgeFlow: Edge-Map Augmented VLM-Based Flowchart Processing for Industrial Requirements Engineering
May 26, 2026Zhifei Dou, Shabnam Hassani, Ou WeiRequirements Engineering Vision-Language Models
Huawei Research Canada
Transforming Privacy Artifacts into Accessible Reports for Non-Technical Stakeholders
May 20, 2026Zoe Pfister, Clemens Sauerwein, Benedikt Dornauer +4Requirements Engineering
University of Innsbruck, Department of Computer Science, Austria · EKS InTec, Germany

Oct 13, 2026J/K move · Enter open · S save

Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents

Kaiming Liu, Yuxuan Liu, Jinrui Ju, Minyuan Ruan+3

College of AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China

LLM Agent Evaluation Software Engineering Agents AI Agent Benchmarks Requirements Engineering

Open paper AskPDF arXiv

Large language model agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomplete. In our analysis of 100 user-agent trajectories from SWE-chat, 56% of initial instructions omit requirements that later emerge as necessary, and 52% of the useful follow-up requirements could have been inferred from the project. A user states requirements from their own understanding of the task, and these stated requirements often differ from the true requirements that completing the task imposes. An agent should therefore treat the instruction as evidence rather than as the objective, inferring the true requirements from the instruction and the environment and satisfying them even when the user is not yet aware of all of them. We call this ability outcome alignment. In this work, we construct TiGanEval, a benchmark of software engineering and research tasks. In every task the user genuinely lacks part of the requirements, each requirement stays discoverable from the code and runtime behaviour of the environment, and requirements the agent infers are separated from those the user adds after observing delivered work. These properties together make outcome alignment measurable. Evaluating eight frontier models including GPT-5.6-Sol, we find outcome alignment broadly missing: the models lose 53 to 67 points of success rate when moving from the full specification to the partial instruction, and consequence feedback across four submissions does not close the gap. Furthermore, a plan-mode harness cannot compensate for the missing ability of the model itself, which places outcome alignment among the abilities the next generation of models should be developed for.