UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories

• URL: http://arxiv.org/abs/2509.11238v1
• Date: Sun, 14 Sep 2025 12:28:39 GMT
• Title: UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories
• Authors: Dongming Jin, Zhi Jin, Yiran Zhang, Zheng Fang, Linyu Li, Yuanpeng He, Xiaohong Chen, Weisong Sun,
• Abstract summary: UserTrace is a system that automatically generates user-level requirements (URs) and recovers live trace links from repositories.<n>Our evaluation shows that UserTrace produces URs with higher completeness, correctness, and helpfulness than an established baseline.
• Score: 41.30731718695494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Software maintainability critically depends on high-quality requirements descriptions and explicit traceability between requirements and code. Although automated code summarization (ACS) and requirements traceability (RT) techniques have been widely studied, existing ACS methods mainly generate implementation-level (i.e., developer-oriented) requirements (IRs) for fine-grained units (e.g., methods), while RT techniques often overlook the impact of project evolution. As a result, user-level (i.e., end user-oriented) requirements (URs) and live trace links remain underexplored, despite their importance for supporting user understanding and for validating whether AI-generated software aligns with user intent. To address this gap, we propose UserTrace, a multi-agent system that automatically generates URs and recovers live trace links (from URs to IRs to code) from software repositories. UserTrace coordinates four specialized agents (i.e., Code Reviewer, Searcher, Writer, and Verifier) through a three-phase process: structuring repository dependencies, deriving IRs for code units, and synthesizing URs with domain-specific context. Our comparative evaluation shows that UserTrace produces URs with higher completeness, correctness, and helpfulness than an established baseline, and achieves superior precision in trace link recovery compared to five state-of-the-art RT approaches. A user study further demonstrates that UserTrace helps end users validate whether the AI-generated repositories align with their intent.

Related papers

• TraceSIR: A Multi-Agent Framework for Structured Analysis and Reporting of Agentic Execution Traces [32.4073751390339]
  We propose TraceSIR, a framework for structured analysis and reporting of agentic execution traces.<n>TraceSIR coordinates three specialized agents: StructureAgent, InsightAgent, and ReportAgent.<n>Experiments show that TraceSIR consistently produces coherent, informative, and actionable reports.
  arXiv  Detail & Related papers  (2026-02-28T12:33:24Z)
• TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability [4.517933493143603]
  This paper introduces TraceLLM, a framework for enhancing requirements traceability through prompt engineering and demonstration selection.<n>We assess prompt generalization and robustness using eight state-of-the-art LLMs on four benchmark datasets.
  arXiv  Detail & Related papers  (2026-02-01T14:29:13Z)
• Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning [65.10602992874787]
  AutoTraj is a framework that automatically learns TIR by repairing and rewarding tool-use trajectories.<n> Experiments on real-world benchmarks demonstrate the effectiveness of AutoTraj.
  arXiv  Detail & Related papers  (2026-01-30T14:42:04Z)
• Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions [8.97512410819274]
  This paper presents the first empirical study on how state-of-the-art multi-agent systems perform in dataset adaptation tasks.<n>We evaluate GitHub Copilot on adapting SE research artifacts from benchmark repositories including ROCODE and LogHub2.0.<n>Results show that current systems can identify key files and generate partial adaptations but rarely produce correct implementations.
  arXiv  Detail & Related papers  (2025-11-26T13:26:11Z)
• Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol [83.83217247686402]
  Large Language Models (LLMs) have evolved from simple text generators into complex software systems that integrate retrieval augmentation, tool invocation, and multi-turn interactions.<n>Their inherent non-determinism, dynamism, and context dependence pose fundamental challenges for quality assurance.<n>This paper decomposes LLM applications into a three-layer architecture: textbftextitSystem Shell Layer, textbftextitPrompt Orchestration Layer, and textbftextitLLM Inference Core.
  arXiv  Detail & Related papers  (2025-08-28T13:00:28Z)
• Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs [17.373348983049176]
  We propose RAGcceptance M2RE, a novel approach to generate acceptance criteria from multi-modal requirements data.<n>We show that our approach effectively reduces manual effort, captures nuanced stakeholder intent, and provides valuable criteria.<n>This research underscores the potential of multi-modal RAG techniques in streamlining software validation processes and improving development efficiency.
  arXiv  Detail & Related papers  (2025-08-09T08:35:40Z)
• Think Like an Engineer: A Neuro-Symbolic Collaboration Agent for Generative Software Requirements Elicitation and Self-Review [23.26988707110507]
  This paper introduces RequireCEG, a requirement elicitation and self-review agent that embeds causal-effect graphs (CEGs) in a neuro-symbolic collaboration architecture.<n>To evaluate our method, we created the RGPair benchmark dataset and conducted extensive experiments.
  arXiv  Detail & Related papers  (2025-07-20T13:59:00Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [54.52092001110694]
  ThinkGeo is a benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>Inspired by tool-interaction paradigms, ThinkGeo includes human-curated queries spanning a wide range of real-world applications.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis [55.390060529534644]
  We propose OS-Genesis, a novel data synthesis pipeline for Graphical User Interface (GUI) agents.<n>Instead of relying on pre-defined tasks, OS-Genesis enables agents first to perceive environments and perform step-wise interactions.<n>We demonstrate that training GUI agents with OS-Genesis significantly improves their performance on highly challenging online benchmarks.
  arXiv  Detail & Related papers  (2024-12-27T16:21:58Z)
• On the Impacts of Contexts on Repository-Level Code Generation [5.641402231731082]
  We present RepoExec, a novel benchmark designed to evaluate repository-level code generation.<n>We focus on three key aspects: executability, functional correctness through comprehensive test case generation, and accurate utilization of cross-file contexts.
  arXiv  Detail & Related papers  (2024-06-17T10:45:22Z)
• Cross-domain Learning Framework for Tracking Users in RIS-aided Multi-band ISAC Systems with Sparse Labeled Data [55.70071704247794]
  Integrated sensing and communications (ISAC) is pivotal for 6G communications and is boosted by the rapid development of reconfigurable intelligent surfaces (RISs) This paper proposes the X2Track framework, where we model the tracking function by a hierarchical architecture, jointly utilizing multi-modal CSI indicators across multiple bands, and optimize it in a cross-domain manner. Under X2Track, we design an efficient deep learning algorithm to minimize tracking errors, based on transformer neural networks and adversarial learning techniques.
  arXiv  Detail & Related papers  (2024-05-10T08:04:27Z)
• Requirements Traceability: Recovering and Visualizing Traceability Links Between Requirements and Source Code of Object-oriented Software Systems [0.0]
  Requirement-to-Code Traceability Links (RtC-TLs) shape the relations between requirement and source code artifacts. This paper introduces YamenTrace, an automatic approach and implementation to recover and visualize RtC-TLs.
  arXiv  Detail & Related papers  (2023-07-09T11:01:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.