Knowledge-Intensive QA

QA: Question Answering

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 48

All topics

ExperienceIndex: Artifact-Grounded Memory
Oct 7, 2026Peter Baile Chen, Geoffrey X. Yu, Xinming Liu +5Memory-Augmented Agents Knowledge-Intensive QA
MIT · McKinsey & Company · Oracle AI & UPenn +1
Return or Revise? Learning When Revision Helps Retrieval-Augmented QA
Sep 24, 2026Nicholas Kashani Motlagh, Tim Anderson, Jeremy Gwinnup +1Retrieval-Augmented Generation LLM Answer Verification
DCS Corp · Air Force Research Laboratory
Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge
Sep 24, 2026Benjamin Gruenbaum, Doron Porat, Assaf Natanzon +3Tool-Augmented Language Model Agents LLM Agent Evaluation
Eon
Meet, Compare, or Abstain: LatWeave for Deterministic Multi-Hop Question Answering on Knowledge Lattices
Sep 23, 2026Yuze Ren, Shaoheng Fan, Tao Wang +2Multi-Hop QA Question Answering
ZenSmart Technology (Beijing) Co., Ltd., China
Potential for Enhanced Learning in Machine Learning Classes by Using Wiki LLM Indexing
Sep 21, 2026Brian WrightRetrieval-Augmented Generation LLM Grounding
School of Data Science, University of Virginia
UniK: Universal Knowledge Perception for Digital and Physical AI
Sep 21, 2026Nirmit Desai, Kunal Sawarkar, Aditya Mahakali +3Multimodal RAG Multimodal IR
AIntropy AI
EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
Sep 14, 2026Cenab Batu Bora, Oylum Alatl\i, Sebnem Bora +1Document Chunking Retrieval-Augmented Generation
Georgia Institute of Technology, Atlanta, GA, USA · Ege University, Izmir, Turkey
ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge
Sep 14, 2026Shreyas Krishnan, Serina Chang, Abhishek NagarajLLM Evaluation Factual Knowledge in Language Models
University of California, Berkeley · National Bureau of Economic Research (NBER)
A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data Analysis
Sep 7, 2026Muhammad Jawad Chowdhury, Md. Sakib KhanSoftware Engineering LLM Prompting
Computer Science and Engineering Islamic University of Technology Dhaka, Bangladesh · Computer Science and Engineering University of Dhaka Dhaka, Bangladesh
mimeo: Compiling Public Expert Corpora into Agent Skills and Testing What Transfers
Aug 31, 2026Timothy KassisTool-Augmented Language Model Agents Personality Modeling in Language Models
K-Dense, Inc.
HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA
Aug 13, 2026Rathijit Aich, Nirjhar Das, Mahfuzulhoq ChowdhuryRetrieval-Augmented Generation Low-Resource Language Processing
Department of Computer Science and Engineering · Chittagong University of Engineering & Technology · Chattogram, Bangladesh
WorkSurface-Bench: Benchmarking Enterprise Agents on Multi-Surface Knowledge Routing
Jul 28, 2026Hao Liang, Meiyi Qiang, Sizhe Qiu +2Computer-Use Agent Benchmarks AI Agent Benchmarks
Peking University · Zhongguancun Academy · University of Chinese Academy of Sciences
ScalableRAG: High-Quality RAG at Zero Ingestion Cost
Jul 27, 2026Hilaf Hasson, Aditya Chakravarty, Jayant Thomas +1Retrieval-Augmented Generation Question Answering
1Cohesity
XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding
Jul 21, 2026Hongchen Wei, Yuanzhe Wang, Bei Liu +9Long-Context Retrieval LLM Evaluation
1Wuhan University · 2Microsoft
ResearchQA: Benchmarking Citation-Grounded Question-Answering on Scientific Papers
Jul 13, 2026Saba Imran, Debanjum Singh SolankyLLM Evaluation Citation Verification
Khoj Inc.
Progressive Disclosure for LLM-Maintained Wiki Knowledge Bases: a Preregistered Ablation
Jul 6, 2026Theodore O. CochranAgentic Retrieval Knowledge-Intensive QA
AI for Altruism (A4A)
KrishokChat: A Citation-Grounded Dataset and Benchmark for Bengali Agricultural Advisory
Jun 28, 2026Khan Raiyan Ibne Reza, Omar Ibne ShahidLLM Grounding Question Answering
North South University Dhaka, Bangladesh
CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks
Jun 19, 2026Ashwin Vinod, Ying Ding, Elias Stengel-EskinLLM Answer Verification LLM Agent Verification
The University of Texas at Austin
Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion
Jun 12, 2026Yi Lu, Zhuofeng Li, Ping Nie +7Agentic Search Agentic Retrieval
University of Toronto · Texas A&M University · University of Waterloo +3
TimeLens: On-Device Artifact Recognition with Retrieval-Augmented Question Answering for the Grand Egyptian Museum
Jun 11, 2026Rawan Hesham, Ali Ashraf, Amr Ahmed +3Real-Time Object Detection Cultural Heritage
Faculty of Computers and AI Capital University Cairo, Egypt
LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
Jun 9, 2026Haonan Wang, Jiaxiang Liu, Yurong Liu +11Multi-Hop QA AI Agent Benchmarks
Columbia University · New York University · Barnard College
Office Comprehension Benchmark
May 29, 2026Firoz Shaik, Mateus Picanço Lima Gomes, Tanvir Aumi +17Document Understanding LLM Evaluation
Microsoft · † Work done while at Microsoft.
Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question Answering
May 28, 2026Shicheng Fan, Haochang Hao, Dehai Min +3Process Reward Models RL for Language Model Reasoning
University of Illinois Chicago
GrepSeek: Training Search Agents for Direct Corpus Interaction
May 28, 2026Alireza Salemi, Chang Zeng, Atharva Nijasure +4Tool-Augmented Language Model Agents Agentic Search
University of Massachusetts Amherst · Princeton University · Carnegie Mellon University
Knowledge Dependency Estimation for Reliable Question Answering
May 27, 2026Chaodong Tong, Qi Zhang, Nannan Sun +2Knowledge-Intensive QA Sensitivity Analysis
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · China Industrial Control Systems Cyber Emergency Response Team, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
May 26, 2026Saptarshi Sengupta, Suhang WangMulti-Hop QA LLM Hallucination Mitigation
The Pennsylvania State University
AuthTrace: Diagnosing Evidence Construction in Thematically Dense Single-Author Corpora
May 25, 2026Xiaoqing Wu, Feifei Li, Haoliang Ming +1Evidence Selection RAG Evaluation
WeChat, Tencent Inc., Beijing, China
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
May 20, 2026Basel Shbita, Pengyuan Li, Anna Lisa GentileVLM Evaluation Visual Question Answering
IBM Research San Jose, CA
SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain
May 18, 2026Lingtao Mao, Huangyu Dai, Xinyu Sun +4Multimodal IR Agentic Search
Kuaishou Technology Beijing, China
AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering
May 17, 2026Taolin Zhang, Dongyang Li, Chen Chen +5Direct Preference Optimization Agentic RAG
School of Computer Science and Information Engineering, Hefei University of Technology · Shanghai University of Electric Power · Guangdong University of Finance and Economics +2

Oct 7, 2026, cs.CLJ/K move · Enter open · S save

ExperienceIndex: Artifact-Grounded Memory

Peter Baile Chen, Geoffrey X. Yu, Xinming Liu, Samuel Madden+4

MIT · McKinsey & Company · Oracle AI & UPenn+1

Memory-Augmented Agents Knowledge-Intensive QA Information Retrieval

Open paper AskPDF arXiv

Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solving traces, but they primarily focus on user preferences, factual attributes, or abstract reasoning patterns rather than persistent artifact-specific knowledge. We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces. ExperienceIndex stores two complementary forms of experience: (i) single-artifact experiences that summarize an artifact's contribution to prior tasks and (ii) artifact-pair experiences that encode structural relationships discovered during past reasoning. Integrated as lightweight middleware, ExperienceIndex uses an experience retrieval mechanism to guide agents toward the complete set of relevant artifacts for new tasks, improving both answer quality and efficiency. Across diverse corpora and agentic solutions with different search frameworks, ExperienceIndex delivers consistent gains, raising answer quality by up to 11.0 points and reducing online dollar cost by up to 50.5%. We further demonstrate two benefits: (i) cross-task generalization, where experiences accumulated from text-to-SQL tasks transfer to factoid QA tasks over the same artifact corpus, and (ii) teacher-student learning, where experiences from a stronger model enable a weaker model to reach comparable performance.

Momentum

Related topics

Latest papers 48