Topic: Awesome List: ai-agent-papers-2026

← Back to home

1. 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...

2. 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...

3. 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...

4. 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...

5. To Retrieve or To Think? An Agentic Approach for Context Evolution

   Paper • Jan 14, 2026 • arxiv.org • Rubing Chen, Jian Wang, Wenjie Li, Xiao-Yong Wei, Qing Li

   Current context augmentation methods, such as retrieval-augmented generation, are essential for solving knowledge-intensive reasoning tasks. However, they typically adhere to a rigid, brute-force s...

6. Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs

   Paper • Jan 13, 2026 • arxiv.org • Manideep Reddy Chinthareddy

   Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as control...

7. OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality in RAG

   Paper • Jan 24, 2026 • arxiv.org • Fengran Mo, Zhan Su, Yuchen Hui, Jinghan Zhang, Jia Ao Sun, Zheyuan Liu, Chao Zhang, Tetsuya Sakai, Jian-Yun Nie

   The development of large language models (LLMs) has achieved superior performance in a range of downstream tasks, including LLM-based retrieval-augmented generation (RAG). The quality of generated ...

8. AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

   Paper • Jan 27, 2026 • arxiv.org • Yupeng Huo, Yaxi Lu, Zhong Zhang, Haotian Chen, Yankai Lin

   Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the per...

9. The AI Hippocampus: How Far are We From Human Memory?

   Paper • Jan 14, 2026 • arxiv.org • Zixia Jia, Jiaqi Li, Yipeng Kang, Yuxuan Wang, Tong Wu, Quansen Wang, Xiaobo Wang, Shuyi Zhang, Junzhe Shen, Qing Li, Siyuan Qi, Yitao Liang, Di He, Zilong Zheng, Song-Chun Zhu

   Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition from static pred...

10. Rethinking Memory Mechanisms of Foundation Agents in the Second Half: A Survey

    Paper • Feb 10, 2026 • arxiv.org • Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang, Yuanchen Bei, Yankai Chen, Tao Feng, Xinyu Pan, Zhen Tan, Yu Wang, Tianxin Wei, Shanglin Wu, Ruiyao Xu, Liangwei Yang, Rui Yang, Wooseong Yang, Chin-Yuan Yeh, Hanrong Zhang, Haozhen Zhang, Siqi Zhu, Henry Peng Zou, Wanjia Zhao, Song Wang, Wujiang Xu, Zixuan Ke, Zheng Hui, Dawei Li, Yaozu Wu, Langzhou He, Chen Wang, Xiongxiao Xu, Baixiang Huang, Juntao Tan, Shelby Heinecke, Huan Wang, Caiming Xiong, Ahmed A. Metwally, Jun Yan, Chen-Yu Lee, Hanqing Zeng, Yinglong Xia, Xiaokai Wei, Ali Payani, Haitong Ma, Wenya Wang, Chenguang Wang, Yu Zhang, Xin Wang, Yongfeng Zhang, Jiaxuan You, Hanghang Tong, Xiao Luo, Xue Liu, Yizhou Sun, Wei Wang, Julian McAuley, James Zou, Jiawei Han, Philip S. Yu, Kai Shu

    The research of artificial intelligence is undergoing a paradigm shift from prioritizing model innovations over benchmark scores towards emphasizing problem definition and rigorous real-world evalu...

11. Continuum Memory Architectures for Long-Horizon LLM Agents

    Paper • Jan 14, 2026 • arxiv.org • Joe Logan

    Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: in...

12. Topo-RAG: Topology-aware retrieval for hybrid text-table documents

    Paper • Jan 15, 2026 • arxiv.org • Alex Dantart, Marco Kóvacs-Navarro

    In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) syst...

13. Structure and Diversity Aware Context Bubble Construction for Enterprise Retrieval Augmented Systems

    Paper • Jan 15, 2026 • arxiv.org • Amir Khurshid, Abhishek Sehgal

    Large language model (LLM) contexts are typically constructed using retrieval-augmented generation (RAG), which involves ranking and selecting the top-k passages. The approach causes fragmentation ...

14. Grounding Agent Memory in Contextual Intent

    Paper • Jan 15, 2026 • arxiv.org • Ruozhen Yang, Yucheng Jiang, Yueqi Jiang, Priyanka Kargupta, Yunyi Zhang, Jiawei Han

    Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent goals and constraints, causing memory...

15. Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration

    Paper • Jan 29, 2026 • arxiv.org • Yuejie Li, Ke Yang, Tao Wang, Bolin Chen, Bowen Li, Chengjun Mao

    Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often chall...

16. Utilizing Metadata for Better Retrieval-Augmented Generation

    Paper • Jan 17, 2026 • arxiv.org • Raquib Bin Yousuf, Shengzhe Xu, Mandar Sharma, Andrew Neeser, Chris Latimer, Naren Ramakrishnan

    Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corp...

17. Augmenting Question Answering with A Hybrid RAG Approach

    Paper • Jan 25, 2026 • arxiv.org • Tianyi Yang, Nashrah Haque, Vaishnave Jonnalagadda, Yuya Jeremy Ong, Zhehui Chen, Yanzhao Wu, Lei Yu, Divyesh Jadav, Wenqi Wei

    Retrieval-Augmented Generation (RAG) has emerged as a powerful technique for enhancing the quality of responses in Question-Answering (QA) tasks. However, existing approaches often struggle with re...

18. Incorporating Q&A Nuggets into Retrieval-Augmented Generation

    Paper • Jan 19, 2026 • arxiv.org • Laura Dietz, Bryan Li, Gabrielle Liu, Jia-Huei Ju, Eugene Yang, Dawn Lawrie, William Walden, James Mayfield

    RAGE systems integrate ideas from automatic evaluation (E) into Retrieval-augmented Generation (RAG). As one such example, we present Crucible, a Nugget-Augmented Generation System that preserves e...

19. SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation

    Paper • Jan 22, 2026 • arxiv.org • Yuxin Yang, Gangda Deng, Ömer Faruk Akgül, Nima Chitsazan, Yash Govilkar, Akasha Tigalappanavara, Shi-Xiong Zhang, Sambit Sahu, Viktor Prasanna

    Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works sca...

20. DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering

    Paper • Jan 23, 2026 • arxiv.org • Haotian Chen, Qingqing Long, Siyu Pu, Xiao Luo, Wei Ju, Meng Xiao, Yuanchun Zhou, Jianghua Zhao, Xuezhi Wang

    With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generati...