Topic: RAG

← Back to home

1. AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents

   Paper • Feb 6, 2026 • arxiv.org • Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster, Bassel Al Omari, Despoina Magka, Alberto Pepe, Alexis Audran-Reiss, Muna Aghamelu, Nicolas Baldwin, Lucia Cipolina-Kun, Jean-Christophe Gagnon-Audet, Chee Hau Leow, Sandra Lefdal, Hossam Mossalam, Abhinav Moudgil, Saba Nazir, Emanuel Tewolde, Isabel Urrego, Jordi Armengol Estape, Amar Budhiraja, Gaurav Chaurasia, Abhishek Charnalia, Derek Dunfield, Karen Hambardzumyan, Daniel Izcovich, Martin Josifoski, Ishita Mediratta, Kelvin Niu, Parth Pathak, Michael Shvartsman, Edan Toledo, Anton Protopopov, Roberta Raileanu, Alexander Miller, Tatiana Shavrina, Jakob Foerster, Yoram Bachrach

   LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from sta...

2. Agentic Uncertainty Reveals Agentic Overconfidence

   Paper • Feb 6, 2026 • arxiv.org • Jean Kaddour, Srijan Patel, Gbètondji Dovonon, Leo Richter, Pasquale Minervini, Matt J. Kusner

   Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agen...

3. From Features to Actions: Explainability in Traditional and Agentic AI Systems

   Paper • Feb 6, 2026 • arxiv.org • Sindhuja Chaduvula, Jessee Ho, Kina Kim, Aravind Narayanan, Mahshid Alinoori, Muskan Garg, Dhanesh Ramachandram, Shaina Raza

   Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structu...

4. SimpleMem: Efficient Lifelong Memory for LLM Agents

   Paper • Jan 29, 2026 • arxiv.org • Jiaqi Liu, Yaofeng Su, Peng Xia, Siwei Han, Zeyu Zheng, Cihang Xie, Mingyu Ding, Huaxiu Yao

   To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via pass...

5. HiMeS: Hippocampus-inspired Memory System for Personalized AI Assistants

   Paper • Jan 6, 2026 • arxiv.org • Hailong Li, Feifei Li, Wenhui Que, Xingyu Fan

   Large language models (LLMs) power many interactive systems such as chatbots, customer-service agents, and personal assistants. In knowledge-intensive scenarios requiring user-specific personalizat...

6. MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

   Paper • Jan 6, 2026 • arxiv.org • Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li

   Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic m...

7. Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents

   Paper • Jan 20, 2026 • arxiv.org • Dehao Tao, Guoliang Ma, Yongfeng Huang, Minghu Jiang

   Human-agent dialogues often exhibit topic continuity-a stable thematic frame that evolves through temporally adjacent exchanges-yet most large language model (LLM) agent memory systems fail to pres...

8. Beyond Static Summarization: Proactive Memory Extraction for LLM Agents

   Paper • Jan 8, 2026 • arxiv.org • Chengyuan Yang, Zequn Sun, Wei Wei, Wei Hu

   Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memor...

9. Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

   Paper • Jan 8, 2026 • arxiv.org • Muzhao Tian, Zisu Huang, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Yuanzhe Shen, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng

   As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems...

10. PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering

    Paper • Jan 9, 2026 • arxiv.org • Yu Liu, Wenxiao Zhang, Cong Cao, Wenxuan Lu, Fangfang Yuan, Diandian Guo, Kun Peng, Qiang Sun, Kaiyan Zhang, Yanbing Liu, Jin B. Hong, Bowen Zhou, Zhiyuan Ma

    Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforcement learning (RL...

11. L-RAG: Balancing Context and Retrieval with Entropy-Based Lazy Loading

    Paper • Jan 10, 2026 • arxiv.org • Sergii Voloshyn

    Retrieval-Augmented Generation (RAG) has emerged as the predominant paradigm for grounding Large Language Model outputs in factual knowledge, effectively mitigating hallucinations. However, convent...

12. Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning

    Paper • Jan 9, 2026 • arxiv.org • Yue Zhou, Xiaobo Guo, Belhassen Bayar, Srinivasan H. Sengamedu

    Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computationally prohibitive. C...

13. CIRAG: Construction-Integration Retrieval and Adaptive Generation for Multi-hop Question Answering

    Paper • Jan 11, 2026 • arxiv.org • Zili Wei, Xiaocui Yang, Yilin Wang, Zihan Wang, Weidong Bao, Shi Feng, Daling Wang, Yifei Zhang

    Triple-based Iterative Retrieval-Augmented Generation (iRAG) mitigates document-level noise for multi-hop question answering. However, existing methods still face limitations: (i) greedy single-pat...

14. Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

    Paper • Jan 11, 2026 • arxiv.org • Hua Ye, Siyuan Chen, Ziqi Zhong, Canran Xiao, Haoliang Zhang, Yuhan Wu, Fei Shen

    Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in practice they often...

15. Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG

    Paper • Jan 12, 2026 • arxiv.org • Manzong Huang, Chenyang Bu, Yi He, Xingrui Zhuo, Xindong Wu

    Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG methods are const...

16. Active Context Compression: Autonomous Memory Management in LLM Agents

    Paper • Jan 12, 2026 • arxiv.org • Nikhil Verma

    Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to "Context Bloat." As interaction history grows, computational costs explode, latency increases,...

17. Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents

    Paper • Jan 12, 2026 • arxiv.org • Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

    Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization. However, existing methods fail to properly mode...

18. Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory

    Paper • Jan 12, 2026 • arxiv.org • Sirui Liang, Pengfei Cao, Jian Zhao, Wenhao Teng, Xiangwen Liao, Jun Zhao, Kang Liu

    Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and re...

19. SwiftMem: Fast Agentic Memory via Query-aware Indexing

    Paper • Jan 13, 2026 • arxiv.org • Anxin Tian, Yiming Li, Xing Li, Hui-Ling Zhen, Lei Chen, Xianzhi Yu, Zhenhua Dong, Mingxuan Yuan

    Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fu...

20. Parallel Context-of-Experts Decoding for Retrieval Augmented Generation

    Paper • Jan 13, 2026 • arxiv.org • Giulio Corallo, Paolo Papotti

    Retrieval Augmented Generation faces a trade-off: concatenating documents in a long prompt enables multi-document reasoning but creates prefill bottlenecks, while encoding document KV caches separa...