Language model agents reason from scratch on every query, discarding their chain of thought after each run. This produces lower accuracy and high variance, as the same query type can succeed or fail unpredictably. We introduce reasoning graphs, a graph structure that persists per-evidence chain of thought as structured edges connected to the evidence items they evaluate. Unlike prior memory mechanisms that retrieve distilled strategies by query similarity, reasoning graphs enable evidence-centric feedback: given a new candidate set, the system traverses all incoming evaluation edges for each evidence item across all prior runs, surfacing how that specific item has been judged before. We further introduce retrieval graphs, a complementary structure that feeds a pipeline planner to tighten the candidate funnel over successive runs. Together, both graphs form a self-improving feedback loop: accuracy improves systematically and verdict-level variance collapses. This requires no retraining; the base model remains frozen and all gains come from context engineering via graph traversal. We evaluate on MuSiQue and HotpotQA using a sequential cluster protocol, a high-reuse deployment simulation, and a determinism experiment. At 50%+ evidence profile coverage, our system reduces errors by 47% compared to vanilla RAG on the same questions (controlled dose-response, p < 0.0001). On 4-hop questions, accuracy improves by +11.0pp (p=0.0001). In high-reuse settings, the system achieves Pareto dominance: highest accuracy, 47% lower cost, and 46% lower latency. Evidence profiles improve verdict consistency by 7-8 percentage points (p=0.007, Wilcoxon); the full system drives all 11 hard probes to perfect consistency at both temperature 0 and 0.5 (p=0.004).
DeepNote: Note-Centric Deep Retrieval-Augmented Generation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Institute for AI, Tsinghua University(清华大学人工智能研究院);South China University of Technology(华南理工大学);Northeastern University(东北大学)
GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework
School of Future Science and Engineering, Soochow University(未来科学与工程学院,苏州大学);School of Mathematical Sciences, Soochow University(数学学院,苏州大学);School of Information Technology (Smart Campus Education Center), Suzhou Institute of Trade & Commerce(信息技术学院(智能校园教育中心),苏州贸易与商业学院)
From RAG to Agentic RAG for Faithful Islamic Question Answering
Qatar Computing Research Institute, HBKU, Qatar(卡塔尔计算研究中心,HBKU,卡塔尔);College of Humanities and Social Sciences, HBKU, Qatar(人文与社会科学学院,HBKU,卡塔尔);Arab Center for Research and Policy Studies, Qatar(阿拉伯研究中心与政策研究所,卡塔尔);College of Islamic Studies, HBKU, Qatar(伊斯兰研究学院,HBKU,卡塔尔);College of Public Policy, HBKU, Qatar(公共政策学院,HBKU,卡塔尔)
GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
Artificial Intelligence Research Institute, Shenzhen University of Advanced Technology(深圳先进技术大学人工智能研究院);Software College, Northeastern University(东北大学软件学院);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
VizRAG: Enhancing Retrieval-Augmented Generation with Hypergraph Visualization
Southern University of Science and Technology(南方科技大学);Hong Kong University of Science and Technology(香港科技大学);Huawei Research(华为研究院);Beihang University(北京航空航天大学)
Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations
Duke–NUS Medical School(杜克-新加坡国立大学医学院);University of Cambridge(剑桥大学);The University of Tokyo(东京大学);Singapore General Hospital(新加坡中央医院);University of Geneva(日内瓦大学);Duke School of Medicine(杜克大学医学院);Duke Clinical Research Institute(杜克临床研究所);Singapore Eye Research Institute(新加坡眼科研究所);Singapore National Eye Center(新加坡国家眼科中心);Stanford University(斯坦福大学);Singapore Health Services(新加坡保健服务集团);National University of Singapore(新加坡国立大学)
Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning
School of Artificial Intelligence, Beihang University(北航人工智能学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院);Beijing Academy of Blockchain and Edge Computing(北京区块链与边缘计算研究院)
DreamerNLplus: Interpretable Modeling of Mental Health Dynamics from Social Media Timelines using Hybrid Rule-Based and RAG Methods
Leiden Institute of Advanced Computer Science (LIACS), Leiden University(莱顿高级计算机科学研究所(LIACS),莱顿大学);School of Computing and Communications (SCC), Lancaster University(计算与通信学院(SCC),兰卡斯特大学);Department of Medical Informatics, Erasmus University Medical Center Rotterdam(医学信息学系,埃因霍温医学中心鲁特万分校);Biomedical Data Sciences, Leiden University Medical Center(生物医学数据科学,莱顿大学医学中心)
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院);Tongyi Lab(通义实验室);Soochow University(苏州大学);University of Oxford(牛津大学);Tsinghua University(清华大学)
Department of Computer Science and Information Engineering, National Taiwan University(国立台湾大学计算机科学与信息工程系);Department of Mathematics, National Kaohsiung Normal University(高雄师范大学数学系);FinTech Center, National Taiwan University(国立台湾大学金融科技中心);E.SUN Financial Holding Co., Ltd.(E.SUN财务公司)