Elamur Research⌕
☰
home / papers / 2026 / Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts

Paper · 2026 · Peijun Qing, Xingjian Diao, Chiyu Ma et al.

Summary

Answering multi-hop questions over long documents requires connecting facts that appear far apart, while ignoring distracting text. Most retrieval-augmented generation (RAG) systems store context in a single format, usually text chunks, which tends to retrieve noisy passages and leads to fragile reasoning. The authors propose TAG (Tailoring Memory Granularity). For each query, TAG pre-builds four memory types at different levels of detail:

  • knowledge triples,
  • atomic facts,
  • summaries,
  • document chunks.

A small reward-model "navigator" then predicts how useful each type is for the question. These predictions become a softmax-normalized weight vector that splits a fixed retrieval budget across the memory types. The navigator is trained on synthetic preference data with a multi-objective Bradley–Terry loss, which learns relative rankings rather than a single best type.

On three long-context multi-hop QA benchmarks, TAG reports state-of-the-art results while adding only about 0.033% extra parameters. This suggests that choosing memory granularity per query is a cheap, practical way to make RAG-based agents reason more reliably.

Key points

  • Memory types and router: the hybrid memory combines triples (entity relations), atomic facts (minimal claims), summaries (global abstraction) and fixed-length chunks (local context). The router outputs weights over these four types, adjusted by a temperature parameter. The weights are turned into integer retrieval counts using a floor operation, and any leftover slots go to the types with the largest fractional parts.
  • Gain over single-format memory: TAG beats single-structure memory by up to 7% on HotPotQA. Retrieval uses Qwen-series embedding models.
  • Loss function comparison: the Bradley–Terry ranking loss gave the best average F1, compared with Cross-Entropy, MSE and BCE alternatives.
  • Sensitivity to Top-K: across K ∈ {25, 50, 75} on HotPotQA, the best result was at K = 50, with F1 of 75.73. Larger budgets brought in more noise.
  • Limitations: the structured memories are generated by a teacher LLM and are not validated, so their errors can carry through to answers. Supervision for the navigator is weak and synthetic. Experiments cover only open-source models.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Dartmouth CollegeHanover · United States37 works · 42,625 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksInformation Systems · 1,437 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Peijun Qing, Xingjian Diao, Chiyu Ma, Saeed Hassanpour and Soroush Vosoughi. 2026. Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.189

@inproceedings{qing2026tailoring,
  title = {{Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts}},
  author = {Peijun Qing, Xingjian Diao, Chiyu Ma, Saeed Hassanpour and Soroush Vosoughi},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.189},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.189}
}

References

105 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Petr Anokhin, Nikita Semenov, Artyom Sorokin, Dmitry Evseev, Mikhail Burtsev, and Evgeny Burnaev. 2024. Arigraph: Learning knowledge graph world models with episodic memory for llm agents. arXiv preprint arXiv:2407.04363. — [arXiv:2407.04363](https://arxiv.org/abs/2407.04363) find
  2. Jihun Baek, Soyeong Lee, Sungmin Kim, Kangwook Lee, and Sungju Kim. 2023. Knowledge graph-enhanced large language models for instruction following. arXiv preprint arXiv:2310.04172. find
  3. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609.
  4. Jinhe Bi, Danqi Yan, Yifan Wang, Wenke Huang, Haokun Chen, Guancheng Wan, Mang Ye, Xun Xiao, Hinrich Schuetze, Volker Tresp, et al. 2025. Cot-kinetics: A theoretical modeling assessing lrm reasoning process. arXiv preprint arXiv:2505.13408. — [arXiv:2505.13408](https://arxiv.org/abs/2505.13408) find
  5. Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning. Springer, New York. find
  6. Ralph Allan Bradley and Milton E. Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324– 345. find
  7. Hanning Chen, Yang Ni, Wenjun Huang, Hyunwoo Oh, Yezi Liu, Tamoghno Das, and Mohsen Imani. 2025. Lvlm_csp: Accelerating large vision language models via clustering, scattering, and pruning for reasoning segmentation. In Proceedings of the 33rd ACM International Conference on Multimedia, pages 3932–3… find
  8. Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, and Dong Yu. 2024. Dense X retrieval: What retrieval granularity should we use? In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
  9. Ming Cheng, Xingjian Diao, Shitong Cheng, and Wenjun Liu. 2024a. Saic: Integration of speech anonymization and identity classification. In AI for Health Equity and Fairness: Leveraging AI to Address Social Determinants of Health, pages 295–306. Springer. find
  10. Ming Cheng, Ziyi Zhou, Bowen Zhang, Ziyu Wang, Jiaqi Gan, Ziang Ren, Weiqi Feng, Yi Lyu, Hefan Zhang, and Xingjian Diao. 2024b. Efflex: Efficient and flexible pipeline for spatio-temporal trajectory graph modeling and representation learning. In Proceedings of the IEEE/CVF Conference on Computer Vis… find
  11. David R. Cox. 1958. The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological), 20(2):215–232. find
  12. Xingjian Diao, Zheyuan Liu, Chunhui Zhang, Weiyi Wu, Keyi Kong, Lin Shi, Kaize Ding, Soroush Vosoughi, and Jiang Gui. 2026. Addressing overthinking in large vision-language models via gated perception-reasoning optimization. arXiv preprint arXiv:2601.04442. find
  13. Xingjian Diao, Weiyi Wu, Keyi Kong, Peijun Qing, Xinwen Xu, Ming Cheng, Soroush Vosoughi, and Jiang Gui. 2025a. Protovqa: An adaptable prototypical framework for explainable fine-grained visual question answering. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Process… find
  14. Xingjian Diao, Chunhui Zhang, Keyi Kong, Weiyi Wu, Chiyu Ma, Zhongyu Ouyang, Peijun Qing, Soroush Vosoughi, and Jiang Gui. 2025b. Soundmind: Rl-incentivized logic reasoning for audio-language models. arXiv preprint arXiv:2506.12935.
  15. Xingjian Diao, Chunhui Zhang, Weiyi Wu, Zhongyu Ouyang, Peijun Qing, Ming Cheng, Soroush Vosoughi, and Jiang Gui. 2025c. Temporal working memory: Query-guided segment refinement for enhanced multimodal understanding. arXiv preprint arXiv:2502.06020. find
  16. Kuicai Dong, Yujing Chang, Derrick Goh Xin Deik, Dexun Li, Ruiming Tang, and Yong Liu. 2025a. MM-DocIR: Benchmarking multimodal retrieval for long documents. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 30971–31005, Suzhou, China. Association for C… find
  17. Kuicai Dong, Yujing Chang, Shijie Huang, Yasheng Wang, Ruiming Tang, and Yong Liu. 2025b. Benchmarking retrieval-augmented multimodal generation for document question answering. Preprint, arXiv:2505.16470. — [arXiv:2505.16470](https://arxiv.org/abs/2505.16470) find
  18. Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee, Hao Zhang, Xiangyang Li, Cong Zhang, and Yong Liu. 2024. MC-indexing: Effective long document retrieval via multi-view content-aware indexing. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 2673–2691, Miami, Florida, US… find
  19. Kuicai Dong, Shurui Huang, Fangda Ye, Wei Han, Zhi Zhang, Dexun Li, Wenjun Li, Qu Yang, Gang Wang, Yichao Wang, Chen Zhang, and Yong Liu. 2025c. Doc-researcher: A unified system for multimodal document parsing and deep research. Preprint, arXiv:2510.21603. — [arXiv:2510.21603](https://arxiv.org/abs/2510.21603) find
  20. Kuicai Dong, Aixin Sun, Jung-jae Kim, and Xiaoli Li. 2023. Open information extraction via chunks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15390–15404, Singapore. Association for Computational Linguistics. find
  21. Kuicai Dong, Zhao Yilin, Aixin Sun, Jung-Jae Kim, and Xiaoli Li. 2021. DocOIE: A document-level context-aware dataset for OpenIE. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2377–2389, Online. Association for Computational Linguistics. find
  22. Jinyuan Fang, Zaiqiao Meng, and Craig MacDonald. 2024. TRACE the evidence: Constructing knowledge-grounded reasoning chains for retrieval-augmented generation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8472–8494, Miami, Florida, USA. Association for Computationa… find
  23. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997.
  24. Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. arXiv preprint arXiv:2405.14831.
  25. Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.
  26. Yangfan He, Jianhui Wang, Yijin Wang, Yan Zhong, Xinyuan Song, Junjiang Lin, Xinhang Yuan, Jingqun Tang, Yi Xin, Hao Zhang, et al. 2025. Enhancing intent understanding for ambiguous prompt: A human-machine co-adaption strategy. arXiv preprint arXiv:2501.15167. — [arXiv:2501.15167](https://arxiv.org/abs/2501.15167) find
  27. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609– 6625.
  28. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  29. Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, and Ping Luo. 2024. Hiagent: Hierarchical working memory management for solving long-horizon agent tasks with large language model. arXiv preprint arXiv:2408.09559.
  30. Sen Hu, Yuxiang Wei, Jiaxin Ran, Zhiyuan Yao, and Lei Zou. 2026. Does memory need graphs? a unified framework and empirical analysis for long-term dialog memory. arXiv preprint arXiv:2601.01280. find
  31. Yucheng Hu and Yuxing Lu. 2024. Rag and rau: A survey on retrieval-augmented language model in natural language processing. arXiv preprint arXiv:2404.19543. — [arXiv:2404.19543](https://arxiv.org/abs/2404.19543) find
  32. Haiduo Huang, Jiangcheng Song, Yadong Zhang, and Pengju Ren. 2025a. Selectkd: Selective token-weighted knowledge distillation for llms. arXiv preprint arXiv:2510.24021. — [arXiv:2510.24021](https://arxiv.org/abs/2510.24021) find
  33. Haiduo Huang, Jiangcheng Song, Wenzhe Zhao, and Pengju Ren. 2025b. Fasteagle: Cascaded drafting for accelerating speculative decoding. arXiv preprint arXiv:2509.20416. — [arXiv:2509.20416](https://arxiv.org/abs/2509.20416) find
  34. Haiduo Huang, Fuwei Yang, Zhenhua Liu, Yixing Xu, Jinze Li, Yang Liu, Xuanwu Yin, Dong Li, Pengju Ren, and Emad Barsoum. 2025c. Jakiro: Boosting speculative decoding with decoupled multi-head via moe. arXiv preprint arXiv:2502.06282. — [arXiv:2502.06282](https://arxiv.org/abs/2502.06282) find
  35. Haiduo Huang, Fuwei Yang, Zhenhua Liu, Xuanwu Yin, Dong Li, Pengju Ren, and Emad Barsoum. 2025d. Specvlm: Fast speculative decoding in vision-language models. arXiv preprint arXiv:2509.11815. — [arXiv:2509.11815](https://arxiv.org/abs/2509.11815) find
  36. Wenjun Huang, Ziteng Cui, Yinqiang Zheng, Yirui He, Tatsuya Harada, and Mohsen Imani. 2025e. Dr. raw: Towards general high-level vision from raw with efficient task conditioning. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. find
  37. Wenjun Huang, Yang Ni, Arghavan Rezvani, SungHeon Jeong, Hanning Chen, Yezi Liu, Fei Wen, and Mohsen Imani. 2025f. Recoverable anonymization for pose estimation: A privacy-enhancing approach. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 5239–5249. IEEE. find
  38. Liu Huanshuo, Hao Zhang, Zhijiang Guo, Jing Wang, Kuicai Dong, Xiangyang Li, Yi Quan Lee, Cong Zhang, and Yong Liu. 2025. CtrlA: Adaptive retrieval-augmented generation via inherent control. In Findings of the Association for Computational Linguistics: ACL 2025, pages 12592–12618, Vienna, Austria. A… find
  39. Priya Jain et al. 2024. Knowledge structure generation and utilization by llms: Emerging methods. arXiv preprint arXiv:2402.03546. — [arXiv:2402.03546](https://arxiv.org/abs/2402.03546) find
  40. Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John F. Canny, and Ian Fischer. 2024. A human-inspired reading agent with gist memory of very long contexts. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net.
  41. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020a. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Pro…
  42. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020b. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474.
  43. Bin Li and Hanjun Deng. 2023. Bilateral personalized dialogue generation with contrastive learning. Soft Computing, 27(6):3115–3132. find
  44. Bin Li, Bin Sun, Shutao Li, Encheng Chen, Hongru Liu, Yixuan Weng, Yongping Bai, and Meiling Hu. 2024a. Distinct but correct: generating diversified and entity-revised medical response. Science China Information Sciences, 67(3):132106. find
  45. Jinze Li, Yixing Xu, Haiduo Huang, Xuanwu Yin, Dong Li, Edith CH Ngai, and Emad Barsoum. 2025a. Gumiho: A hybrid architecture to prioritize early tokens in speculative decoding. arXiv preprint arXiv:2503.10135. — [arXiv:2503.10135](https://arxiv.org/abs/2503.10135) find
  46. Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, et al. 2024b. Graphreader: Building graph-based agent to enhance long-context abilities of large language models. arXiv preprint arXiv:2406.14550. find
  47. Shutao Li, Bin Li, Bin Sun, and Yixuan Weng. 2024c. Towards visual-prompt temporal answer grounding in instructional video. IEEE transactions on pattern analysis and machine intelligence, 46(12):8836– 8853. find
  48. Xiang Li et al. 2023. Structured knowledge generation by large language models. arXiv preprint arXiv:2310.08547. — [arXiv:2310.08547](https://arxiv.org/abs/2310.08547) find
  49. Xiangyang Li, Kuicai Dong, Yi Quan Lee, Wei Xia, Hao Zhang, Xinyi Dai, Yasheng Wang, and Ruiming Tang. 2025b. CoIR: A comprehensive benchmark for code information retrieval models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag…
  50. Xianhang Li, Yanqing Liu, Haoqin Tu, and Cihang Xie. 2025c. Openvision: A fully-open, cost-effective family of advanced vision encoders for multimodal learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 3977–3987. find
  51. Yanshu Li, Yi Cao, Hongyang He, Qisen Cheng, Xiang Fu, Xi Xiao, Tianyang Wang, and Ruixiang Tang. 2025d. M²IV: Towards efficient and fine-grained multimodal in-context learning via representation engineering. In Second Conference on Language Modeling. find
  52. Yanshu Li, Jianjiang Yang, Tian Yun, Pinyuan Feng, Jinfa Huang, and Ruixiang Tang. 2025e. Taco: Enhancing multimodal in-context learning via task mapping-guided sequence configuration. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 736–763.
  53. Zhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin, Yaojie Lu, Qiaoyu Tang, Fei Huang, Xianpei Han, Le Sun, and Yongbin Li. 2024d. Structrag: Boosting knowledge intensive reasoning of llms via inference-time hybrid information structurization. find
  54. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2023. Lost in the middle: How language models use long contexts. arXiv preprint arXiv:2307.03172.
  55. Yanqing Liu, Xianhang Li, Zeyu Wang, Bingchen Zhao, and Cihang Xie. 2024. Clips: An enhanced clip framework for learning with synthetic captions. arXiv preprint arXiv:2411.16828. — [arXiv:2411.16828](https://arxiv.org/abs/2411.16828) find
  56. Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, and Cihang Xie. 2025. Openvision 2: A family of generative pretrained visual encoders for multimodal learning. arXiv preprint arXiv:2509.01644. — [arXiv:2509.01644](https://arxiv.org/abs/2509.01644) find
  57. Chiyu Ma, Enpei Zhang, Yilun Zhao, Wenjun Liu, Yaning Jia, Peijun Qing, Lin Shi, Arman Cohan, Yujun Yan, and Soroush Vosoughi. 2025. Judging with many minds: Do more perspectives mean less prejudice? arXiv preprint arXiv:2505.19477. — [arXiv:2505.19477](https://arxiv.org/abs/2505.19477) find
  58. Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, Pang Wei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference on Empirical Methods in Natur…
  59. Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G Patil, Ion Stoica, and Joseph E Gonzalez. 2023. Memgpt: Towards llms as operating systems. arXiv preprint arXiv:2310.08560. find
  60. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023. find
  61. Peijun Qing, Chongyang Gao, Yefan Zhou, Xingjian Diao, Yaoqing Yang, and Soroush Vosoughi. 2024. Alphalora: Assigning lora experts based on layer training quality. find
  62. Ohad Rubin, Jonathan Herzig, and Jonathan Berant. 2022. Learning to retrieve prompts for in-context learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2655–2671.
  63. Claude E. Shannon. 1948. A mathematical theory of communication. Bell System Technical Journal, 27(3):379–423. find
  64. Fobo Shi, Peijun Qing, Dong Yang, Nan Wang, Youbo Lei, Haonan Lu, Xiaodong Lin, and Duantengchuan Li. 2024. Prompt space optimizing few-shot reasoning success with large language models. In Findings of the Association for Computational Linguistics: NAACL 2024. find
  65. Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, 36:8634–8652.
  66. Ava Spataru, Eric Hambro, Elena Voita, and Nicola Cancedda. 2024. Know when to stop: A study of semantic drift in text generation. arXiv preprint arXiv:2404.05411. find
  67. Zhen Sun, Runjin Wang, Siyuan Chen, Kexuan Wang, Kaisheng Feng, Chonggang Wang, Shimin Shi, Yejin Zhang, Xin Huang, Yu Zhang, et al. 2024. Structgpt: A general framework for large language model to reason over structured data. arXiv preprint arXiv:2402.00818. find
  68. Yijun Tian, Shaoyu Chen, Zhichao Xu, Yawei Wang, Jinhe Bi, Peng Han, and Wei Wang. 2025. Reinforcement mid-training. Preprint, arXiv:2509.24375. — [arXiv:2509.24375](https://arxiv.org/abs/2509.24375) find
  69. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. find
  70. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. In Proceedings of the Annual Meeting of the Association for Computational Linguistics.
  71. Narayan S Umanath and Iris Vessey. 1994. Multiattribute data presentation and human judgment: A cognitive fit perspective. Decision Sciences, 25(5-6):795–824. find
  72. Iris Vessey. 1991. Cognitive fit: A theory-based analysis of the graphs versus tables literature. Decision Sciences, 22(2):219–240. find
  73. Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, and Tong Zhang. 2024a. Arithmetic control of llms for diverse user preferences: Directional preference alignment with multi-objective rewards. In Association for Computational Linguistics.
  74. Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, and Tong Zhang. 2024b. Interpretable preferences via multi-objective reward modeling and mixture-of-experts. arXiv preprint arXiv:2406.12845.
  75. Junxi Wang, Jize Liu, Na Zhang, and Yaxiong Wang. 2025a. Consistency-aware fake videos detection on short video platforms. In International Conference on Intelligent Computing, pages 200–210. Springer. find
  76. Junxi Wang, Yaxiong Wang, Lechao Cheng, and Zhun Zhong. 2025b. Fakesv-vlm: Taming vlm for detecting fake short-video news via progressive mixture-of-experts adapter. arXiv preprint arXiv:2508.19639. find
  77. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. 2024c. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6):186345.
  78. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Luo, Wayne Xin Tian, Miaohua Niu, Le Wu, Keyu Wang, Shucheng Wang, and Lining Wang. 2023a. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432.
  79. Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Polak Scowcroft, Neel Kant, Aidan Swope, and Oleksii Kuchaiev. 2023b. Helpsteer: Multi-attribute helpfulness dataset for steerlm. Preprint, arXiv:2311.09528.
  80. Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, and Vince D Calhoun. 2025a. 4d multimodal co-attention fusion network with latent contrastive alignment for alzheimer’s diagnosis. arXiv preprint arXiv:2504.16798. — [arXiv:2504.16798](https://arxiv.org/abs/2504.16798) find
  81. Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, and Vince D Calhoun. 2025b. More-brain: Routed mixture of experts for interpretable and generalizable cross-subject fmri visual decoding. arXiv preprint arXiv:2505.15946. — [arXiv:2505.15946](https://arxiv.org/abs/2505.15946) find
  82. Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Lucas A Salas, and Jiang Gui. 2025. Assessing and mitigating medical knowledge drift and conflicts in large language models. arXiv preprint arXiv:2505.07968. find
  83. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  84. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. 2025. The rise and potential of large language model based agents: A survey. Science China Information Sciences, 68(2):121101.
  85. Wulin Xie, Xiaohuan Lu, Yadong Liu, Jiang Long, Bob Zhang, Shuping Zhao, and Jie Wen. 2024. Uncertainty-aware pseudo-labeling and dual graph driven network for incomplete multi-view multi-label classification. In Proceedings of the 32nd ACM international conference on multimedia, pages 6656– 6665. find
  86. Wulin Xie, Yi-Fan Zhang, Chaoyou Fu, Yang Shi, Bingyan Nie, Hongkai Chen, Zhang Zhang, Liang Wang, and Tieniu Tan. 2025a. Mme-unify: A comprehensive benchmark for unified multimodal understanding and generation models. arXiv preprint arXiv:2504.03641. — [arXiv:2504.03641](https://arxiv.org/abs/2504.03641) find
  87. Wulin Xie, Lian Zhao, Jiang Long, Xiaohuan Lu, and Bingyan Nie. 2025b. Multi-view factorizing and disentangling: A novel framework for incomplete multi-view multi-label classification. In 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 1914–1923. IEEE. find
  88. Yikang Xu, Shuyuan Li, J D Choi, and M Coyle. 2023. Memorysandbox: A unified framework for diverse agent memory. arXiv preprint arXiv:2312.10272. — [arXiv:2312.10272](https://arxiv.org/abs/2312.10272) find
  89. Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schütze, Volker Tresp, and Yunpu Ma. 2026. Memory-r1: Enhancing large language model agents to manage and utilize memories via reinforcement learning. Preprint,…
  90. Dong Yang, Peijun Qing, Yang Li, Haonan Lu, and Xiaodong Lin. 2022. Gammae: Gamma embeddings for logical queries on knowledge graphs. find
  91. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–…
  92. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629.
  93. Xiangchi Yuan, Xiang Chen, Tong Yu, Dachuan Shi, Can Jin, Wenke Lee, and Saayan Mitra. 2025a. Mitigating forgetting between supervised and reinforcement learning yields stronger reasoners. arXiv preprint arXiv:2510.04454. — [arXiv:2510.04454](https://arxiv.org/abs/2510.04454) find
  94. Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu, Dachuan Shi, Leyan Pan, Soroush Vosoughi, and Wenke Lee. 2025b. Superficial self-improved reasoners benefit from model merging. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5912–5932.
  95. Ruihong Zeng, Jinyuan Fang, Siwei Liu, and Zaiqiao Meng. 2024. On the structural memory of llm agents. arXiv preprint arXiv:2412.15266. — [arXiv:2412.15266](https://arxiv.org/abs/2412.15266) find
  96. Hao Zhang, Bo Huang, Zhenjia Li, Xi Xiao, Hui Yi Leong, Zumeng Zhang, Xinwei Long, Tianyang Wang, and Hao Xu. 2025a. Sensitivity-lora: Low-load sensitivity-based fine-tuning for large language models. arXiv preprint arXiv:2509.09119. find
  97. Hao Zhang, Zhenjia Li, Runfeng Bao, Yifan Gao, Xi Xiao, Heng Zhang, Shuyang Zhang, Bo Huang, Yuhang Wu, Tianyang Wang, et al. 2025b. Hyperadalora: Accelerating lora rank allocation during training via hypernetworks without sacrificing performance. arXiv preprint arXiv:2510.02630.
  98. Hao Zhang, Mengsi Lyu, Bo Huang, Yulong Ao, and Yonghua Lin. 2025c. Trimtokenator-lc: Towards adaptive visual token pruning for large multimodal models with long contexts. arXiv preprint arXiv:2512.22748. — [arXiv:2512.22748](https://arxiv.org/abs/2512.22748) find
  99. Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Zijian Zhang, Yilei Yuan, Hao Zhang, and Jin Huang. 2025d. Can representation gaps be the key to enhancing robustness in graph-text alignment? arXiv preprint arXiv:2510.12087. — [arXiv:2510.12087](https://arxiv.org/abs/2510.12087) find
  100. Wenlin Zhang, Xiangyang Li, Kuicai Dong, Yichao Wang, Pengyue Jia, Xiaopeng Li, Yingyi Zhang, Derong Xu, Zhaocheng Du, Huifeng Guo, Ruiming Tang, and Xiangyu Zhao. 2025e. Process vs. outcome reward: Which is better for agentic rag reinforcement learning. Preprint, arXiv:2505.14069. — [arXiv:2505.14069](https://arxiv.org/abs/2505.14069) find
  101. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2024. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501. find
  102. Qingfei Zhao, Ruobing Wang, Yukuo Cen, Daren Zha, Shicheng Tan, Yuxiao Dong, and Jie Tang. 2024. LongRAG: A dual-perspective retrieval-augmented generation paradigm for long-context question answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. find
  103. Changshi Zhou, Feng Luan, Jiarui Hu, Shaoqiang Meng, Zhipeng Wang, Yanchao Dong, Yanmin Zhou, and Bin He. 2025a. Learning efficient robotic garment manipulation with standardization. arXiv preprint arXiv:2506.22769. — [arXiv:2506.22769](https://arxiv.org/abs/2506.22769) find
  104. Changshi Zhou, Haichuan Xu, Ningquan Gu, Zhipeng Wang, Bin Cheng, Pengpeng Zhang, Yanchao Dong, Mitsuhiro Hayashibe, Yanmin Zhou, and Bin He. 2025b. Language-guided long horizon manipulation with llm-based planning and visual perception. arXiv preprint arXiv:2509.02324. — [arXiv:2509.02324](https://arxiv.org/abs/2509.02324) find
  105. Yixiao Zhou, Ziyu Zhao, Dongzhou Cheng, Zhiliang Wu, Jie Gui, Yi Yang, Fei Wu, Yu Cheng, and Hehe Fan. 2025c. Dropping experts, recombining neurons: Retraining-free pruning for sparse mixture-of-experts llms. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15169– 1518… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/qing-2026-tailoring-memory-granularity-multi-hop/