Case-Based Reasoning

Follow this topic Ask about this topic

Latest papers

12 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
Sep 17, 2026Mingxuan Zhang, Xiaowen Wang, Anupma Sharan +4Case-Based Reasoning Retrieval-Augmented Generation
Microsoft, Redmond, WA, USA
Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
May 21, 2026Yiming Xu, Yixuan Liu, Yuhang Zhang +3Case-Based Reasoning Medical Image Classification
University of Science and Technology of China · Hefei, China
Evidential Reasoning Advances Interpretable Real-World Disease Screening
May 14, 2026Chenyu Lian, Hong-Yu Zhou, Jing QinCase-Based Reasoning Medical Image Analysis
The Center for Smart Health, School of Nursing, the Hong Kong Polytechnic University, Hong Kong, China · Research Institute for Smart Ageing, the Hong Kong Polytechnic University, Hong Kong, China · School of Biomedical Engineering, Tsinghua Medicine, Tsinghua University, Beijing, China
Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
May 14, 2026Renning Pang, Tian Lan, Leyuan Liu +3Case-Based Reasoning Language Model Calibration
University of Electronic Science and Technology of China, Chengdu 611731, China
Deep Arguing
May 11, 2026Adam Gould, Francesca ToniCase-Based Reasoning Neural Network Interpretability
Department of Computing Imperial College London
Alignment as Jurisprudence
May 8, 2026Nicholas CaputoCase-Based Reasoning LLM Alignment
Researcher – Legal Alignment on Frontier AI at the Oxford Martin AI Governance Initiative
Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning
Apr 14, 2026Zhenyu Ma, Yuyang Song, Chunyi Yang +3Case-Based Reasoning LLM Agents
National Glycoengineering Research Center, Shandong University, Qingdao 266237, China. · State Key Laboratory of Microbial Technology, Shandong University, Qingdao 266237, China.
Event-Centric World Modeling with Memory-Augmented Retrieval for Embodied Decision-Making
Apr 8, 2026Zhaowen Fan, Rongchao Zhang, Yunxiang HanCase-Based Reasoning Embodied Navigation
School of Computer Science, Sichuan University, Chengdu 610065, China
GraphWalker: Patient Analogy Meets Information Gain for Clinical Reasoning with Large Language Models
Apr 8, 2026Yue Fang, Weibin Liao, Yuxin Guo +8Case-Based Reasoning Clinical Reasoning
School of Computer Science, Peking University, Beijing, China · National Engineering Research Center for Software Engineering, Peking University, Beijing, China
DomAgent: Leveraging Knowledge Graphs and Case-Based Reasoning for Domain-Specific Code Generation
Mar 22, 2026Shuai Wang, Dhasarathy Parthasarathy, Robert Feldt +1Case-Based Reasoning Code Generation
Chalmers University of Technology, Gothenburg, Sweden · Volvo Group, Gothenburg, Sweden
CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain
Mar 5, 2026Hung Nguyen, Hans Moen, Pekka MarttinenCase-Based Reasoning Text-to-SQL
Department of Computer Science Aalto University · Department of Clinical Medicine Aalborg University
MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrieval
Feb 28, 2026Shuheng Chen, Namratha Patil, Haonan Pan +4Case-Based Reasoning Clinical Decision Support
University of Southern California

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

RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents

Mingxuan Zhang, Xiaowen Wang, Anupma Sharan, Zhengyi Chen+3

Microsoft, Redmond, WA, USA

Case-Based Reasoning Retrieval-Augmented Generation State Tracking RAG Evaluation

Open paper AskPDF arXiv

Effective troubleshooting agents in enterprise customer support depend on retrieving actionable guidance from similar historical cases, yet existing retrieval-augmented generation (RAG) systems treat support cases as static documents and overlook their multi-stage, stateful nature. We introduce RAFT (Retrieval-Augmented Framework for Troubleshooting Agents), a stateful RAG framework that abstracts each closed historical case into a directed chain of timeline entries and retrieves at the entry level, surfacing cases whose intermediate states match the active case and returning the parent-case trajectory anchored at the matched state; an optional case-level graph links cases through a configurable similarity representation. We evaluate this retrieval layer directly, which, unlike evaluating a full agent system, requires no production deployment. Because public multi-stage troubleshooting data is extremely rare, we pair a synthetic benchmark built from Microsoft Learn Windows Server documentation with real Apache Jira issues carrying human-created duplicate labels. RAFT improves Case Hit over vanilla RAG and GraphRAG baselines at every stage of case progress, with statistically significant gains over the strongest baseline; the Jira results provide directional evidence that the advantage transfers to real case histories. We release our benchmark, implementation, and the Apache Jira evaluation set.