# 数字教材·各章「前沿文献（近三年 2023–2026）」候选清单

> 数据源说明：Google Scholar 无公开 API 且封爬，改用 OpenAlex（开放 API，覆盖相当）为主、WebSearch（即 Google Scholar 检索入口）回退。以下均为真实文献，链接指向原文/预印本/出处。
> 状态：候选阶段，待用户确认插入方式后注入各章 `知识拓展与前沿` 模块。

---

## 第1章 信息系统与智能体导论
1. Xi et al. (2023). *The Rise and Potential of Large Language Model Based Agents: A Survey*. arXiv:2309.02186 — 奠定"脑–感知–行动"智能体栈，最常被引用的入门综述。https://arxiv.org/abs/2309.02186
2. Wang et al. (2024). *A Survey on Large Language Model based Autonomous Agents*. Frontiers of Computer Science. arXiv:2308.11432 — 单智能体规划/多智能体协作/人在回路的系统分类。https://arxiv.org/abs/2308.11432
3. Chowa et al. (2025/2026). *From Language to Action: A Review of LLMs as Autonomous Agents and Tool Users*. Artificial Intelligence Review. arXiv:2508.17281 — 聚焦 2023–2025 A*/A 会议与 Q1 期刊，覆盖架构/工具/认知机制。https://arxiv.org/abs/2508.17281
4. Li, X. (2025). *A Review of Prominent Paradigms for LLM-Based Agents: Tool Use, Planning, and Feedback Learning*. COLING 2025 — 工具使用(含RAG)/规划/反馈学习三大范式综述。https://www.deepnlp.org/store/ai-agent/autonomous-agent/pub-xinzhel/llm-agent-survey
5. Sun et al. (2025). *LLM-Based Agents for Tool Learning: A Survey* — 200+ 工具增强智能体工作的统一评测协议。

## 第2章 信息系统规划与可行性
1. Owusu, A. (2024). *Assessing the Implementation Success of Strategic Information Systems Planning (SISP) in Ghanaian Organizations*. SAGE Open, 14(3). DOI:10.1177/21582440241275957 — 业务–IT 战略对齐、高层承诺、跨部门协作是 SISP 成功关键。https://doi.org/10.1177/21582440241275957
2. Carter, L., Desouza, K.C., Dawson, G.S., Pardo, T. (2024). *Digital transformation of the public sector: Designing strategic information systems*. The Journal of Strategic Information Systems, 33(3), 101853. https://doi.org/10.1016/j.jsis.2024.101853
3. Sundberg, L., Holmström, J. (2024). *Fusing domain knowledge with machine learning: A public sector perspective*. JSIS, 33(3), 101848 — 领域知识+ML 融合对 IS 规划的影响。https://doi.org/10.1016/j.jsis.2024.101848
4. Senyo, P.K., Karanasios, S., Agbloyor, E.K., Choudrie, J. (2024). *Government-Led digital transformation in FinTech ecosystems*. JSIS, 33(3), 101849. https://doi.org/10.1016/j.jsis.2024.101849
5. Sabir, S. (2025). *Implementing a SISP Framework at Veolia*. ScienceDirect — 企业级 SISP 落地案例（BSP→SISP，CMMI 五级）。https://www.sciencedirect.com/science/article/pii/S1947818625000328

## 第3章 需求分析（需求工程）
1. Zadenoori et al. (2025). *LLMs for Requirements Engineering: A Systematic Literature Review*. arXiv:2509.11446 — 74 篇主研究(2023–2024)的系统综述，含提示策略/评估方法。https://arxiv.org/abs/2509.11446
2. Hemmat et al. (2025). *Research directions for using LLM in software requirement engineering: a systematic review*. Frontiers in Computer Science. https://frontiersin.org/journals/computer-science/articles/10.3389/fcomp.2025.1519437/full
3. Luitel et al. (2024). *Improving requirements completeness: Automated assistance through large language models*. Requirements Engineering, 29, 73–95. DOI:10.1007/s00766-024-00416-3 — 需求完整性自动辅助。https://doi.org/10.1007/s00766-024-00416-3
4. Ronanki et al. (2023). *Investigating ChatGPT's Potential to Assist in Requirements Elicitation Processes* — 需求获取辅助。https://www.connectedpapers.com/main/ba71fb0fa68ab7d566dd4bbc6ab27efe7a1ff4a9/Using-ChatGPT-in-Software-Requirements-Engineering%3A-A-Comprehensive-Review/graph
5. Zhu et al. (2025). *ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation* — 智能体自动生成软件需求规格。

## 第4章 智能体架构设计
1. Hassouna et al. (2024). *LLM-Agent-UMF: A Unified Framework for LLM-based Agents*. Information Fusion — 五模块核心智能体：规划/记忆/画像/行动/安全。https://www.emergentmind.com/topics/llm-based-agent-frameworks
2. Yao et al. (2023). *ReAct: Synergizing Reasoning and Acting in Language Models*. ICLR 2023. arXiv:2210.03629 — 推理+行动循环的奠基模式。https://arxiv.org/abs/2210.03629
3. Shinn et al. (2023). *Reflexion: Language Agents with Verbal Reinforcement Learning*. NeurIPS 2023. arXiv:2303.11366 — 自我反思/自我修正闭环。https://arxiv.org/abs/2303.11366
4. Wang et al. (2023). *Voyager: An Open-Ended Embodied Agent with Large Language Models*. arXiv:2305.16291 — 终身学习与自主技能库。https://arxiv.org/abs/2305.16291
5. emergentmind (2025). *LLM-Based Agent Frameworks* — 感知–规划–行动–记忆模块化与设计范式综述。http://www.emergentmind.com/topics/llm-based-agent-frameworks

## 第5章 提示词工程与 RAG
1. Gao et al. (2024). *Retrieval-Augmented Generation for Large Language Models: A Survey*. arXiv:2312.10997 — 朴素/高级/模块化三范式权威综述。https://arxiv.org/abs/2312.10997
2. Tian et al. (2025). *从RAG到SAGE：现状与展望*. 自动化学报, 51(6):1145–1169. DOI:10.16383/j.aas.c240163 — 中文顶刊，RAG 原理+拓展框架 SAGE。https://www.aas.net.cn/cn/article/pdf/preview/10.16383/j.aas.c240163.pdf
3. BAAI (2024). *一文搞懂RAG技术的5种范式* — Naive/Advanced/Modular/Graph/Agentic RAG。https://hub.baai.ac.cn/view/43613
4. Jin et al. (2024). *FlashRAG: A Modular Toolkit for Efficient RAG Research*. arXiv:2405.13576 — 12 种 RAG 方法+32 数据集模块化工具包。https://arxiv.org/abs/2405.13576
5. Zhao et al. (2024). *Retrieval-Augmented Generation for AI-Generated Content: A Survey*. arXiv:2402.19473 — AIGC 视角的 RAG 综述。https://arxiv.org/abs/2402.19473

## 第6章 智能体记忆与多模态
1. Zhang et al. (2024). *A Survey on the Memory Mechanism of LLM based Agents*. arXiv:2404.13565 — 记忆机制系统综述。https://arxiv.org/abs/2404.13565
2. Xu et al. (2025). *A-MEM: Agentic Memory for LLM Agents*. arXiv:2502.12110 — Zettelkasten 式动态链接记忆，支持记忆演化。https://arxiv.org/abs/2502.12110
3. Wang et al. (2025). *MIRIX: A Multimodal Agentic Memory System*. arXiv:2507.07957 — 六类记忆+多智能体+多模态。https://arxiv.org/abs/2507.07957
4. Long et al. (2025). *M3-Agent: A Multimodal Agent with Long-Term Memory*. arXiv:2508.09736 — 实体中心多模态长期记忆+强化学习。https://arxiv.org/abs/2508.09736
5. Jain et al. (2025). *AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory*. LAW@NeurIPS 2025. arXiv:2510.15261 — 图结构多模态情境记忆。https://arxiv.org/abs/2510.15261

## 第7章 多智能体协作
1. Wu et al. (2023). *AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation*. arXiv:2308.08155 — 微软对话式多智能体框架事实标准。https://arxiv.org/abs/2308.08155
2. Hong et al. (2024). *MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework*. ICLR 2024. arXiv:2308.00352 — 标准化作业流程(SOP)驱动的软件工厂模式。https://arxiv.org/abs/2308.00352
3. Chen et al. (2024). *ChatDev: Communicative Agents for Software Development*. arXiv:2307.07924 — 角色对话协作开发。https://arxiv.org/abs/2307.07924
4. Li et al. (2023). *CAMEL: Communicative Agents for "Mind" Exploration*. NeurIPS 2023. arXiv:2303.17760 — 首个角色扮演多智能体协作框架。https://arxiv.org/abs/2303.17760
5. Google Research (2024). *Chain-of-Agents (CoA): LLM Collaborating on Long-Context Tasks* — 链式推理缓解长文本"中段遗失"。

## 第8章 低代码/无代码与 AI 编程
1. White et al. (2023). *ChatGPT Prompt Patterns for Improving Code Quality, Refactoring, Requirements Elicitation, and Software Design*. Springer — 提示词模式提升代码质量/重构/设计。https://www.connectedpapers.com/main/ba71fb0fa68ab7d566dd4bbc6ab27efe7a1ff4a9/Using-ChatGPT-in-Software-Requirements-Engineering%3A-A-Comprehensive-Review/graph
2. 美团 NoCode (2025). *对话式 AI 编程智能体，零代码全栈生成* — 产业实践：AI 原生无代码。https://finance.sina.cn/2025-05-30/detail-ineyipfa8707225.d.html
3. 百度 秒哒 (2024–2025). *多智能体协作的无代码应用搭建平台* — 产业实践：对话式无代码。https://aiproducthub.cn/sites/miaoda-ai-app-builder-features-usage-experience.html
4. Hagel et al. (2024). *Turning Low-Code into No-Code with LLMs* — LLM 将低代码升级为无代码。
5. Käss et al. (2023). *Low-code adoption factors* — 低代码平台采纳影响因素研究（OpenAlex）。

## 第9章 测试、项目管理与运维
1. Chu et al. (2025/2026). *Large Language Models for Unit Test Generation: Achievements, Challenges, and Opportunities*. SLR of 115 papers (2021–2025). arXiv:2511.21382 — 单元测试生成生命周期分类+自主测试智能体路线。https://arxiv.org/abs/2511.21382
2. Augusto et al. (2025). *Large Language Models for Software Testing: A Research Roadmap*. arXiv:2509.25043 — LLM 测试半系统综述+研究路线。https://arxiv.org/abs/2509.25043
3. TAPD AI (2025, 腾讯). *AI 全链路敏捷研发：需求→DevOps 量化效能提升* — 产业：AI 重构研发流程。https://cloud.tencent.com/developer/article/2677210
4. Testin XAgent (2025). *大模型+多模态智能体的"无人测试"系统* — 产业：自然语言生成测试+探索式测试。https://so.html5.qq.com/page/real/search_news?docid=70000021_03268cd723b32652
5. Wu et al. (2023). *Large Language Models in Fault Localisation*. arXiv:2308.15276 — LLM 故障定位。https://arxiv.org/abs/2308.15276

---

### 待确认事项（请在回复中告知）
- 插入位置：① 在「知识拓展与前沿」模块内新增子板块（推荐）；② 作为独立新模块（课程思政之前）；③ 附在「本章小结」之后。
- 每章篇数：① 4–5 篇精选（推荐）；② 全部 ~5–6 篇；③ 3 篇极简。
- 呈现形式：① 中文译名+原文标题+作者/年份/出处+外链（推荐）；② 仅中文标题+出处，无外链；③ 仅标题+年份清单。