CFP last date
20 February 2026
Call for Paper
March Edition
IJCA solicits high quality original research papers for the upcoming March edition of the journal. The last date of research paper submission is 20 February 2026

Submit your paper
Know more
The week's pick
Responsive image
A Knowledge-Graph–Driven Multimodal Large Model for Semantic Understanding and Controllable Generation of Intangible Cultural Heritage

Jundi Yang Heng Yao
Random Articles
Reseach Article

Self-Reflective Memory Consolidation in Agentic Architectures

by Vijay Putta, Krishna Teja Areti, Ajay Guyyala, Prudhvi Ratna Badri Satya
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 73
Year of Publication: 2026
Authors: Vijay Putta, Krishna Teja Areti, Ajay Guyyala, Prudhvi Ratna Badri Satya
10.5120/ijca2026926236

Vijay Putta, Krishna Teja Areti, Ajay Guyyala, Prudhvi Ratna Badri Satya . Self-Reflective Memory Consolidation in Agentic Architectures. International Journal of Computer Applications. 187, 73 ( Jan 2026), 1-14. DOI=10.5120/ijca2026926236

@article{ 10.5120/ijca2026926236,
author = { Vijay Putta, Krishna Teja Areti, Ajay Guyyala, Prudhvi Ratna Badri Satya },
title = { Self-Reflective Memory Consolidation in Agentic Architectures },
journal = { International Journal of Computer Applications },
issue_date = { Jan 2026 },
volume = { 187 },
number = { 73 },
month = { Jan },
year = { 2026 },
issn = { 0975-8887 },
pages = { 1-14 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number73/self-reflective-memory-consolidation-in-agentic-architectures/ },
doi = { 10.5120/ijca2026926236 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-01-20T22:56:18.634496+05:30
%A Vijay Putta
%A Krishna Teja Areti
%A Ajay Guyyala
%A Prudhvi Ratna Badri Satya
%T Self-Reflective Memory Consolidation in Agentic Architectures
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 73
%P 1-14
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This work introduces a Self-Reflective Memory Architecture (SRMA) that maintains coherence and retention across long reasoning cycles by integrating episodic encoding, reflection scoring, adaptive retrieval, and energy-based correction into a unified consolidation process. SRMA preserved alignment between stored and retrieved representations, yielding a retention alignment of ρ = 0.91, reflective drift Ψ = 0.048, and reflective efficiency Ω = 0.89 across MemoryBank, LME, and DuLeMon. Standard evaluation metrics remained consistently high, with accuracy 0.91, precision 0.91, recall 0.89, and F1 0.90/0.87. Reconstruction and energy losses were reduced to Lrec = 0.017 and Lenergy = 0.014, indicating stable consolidation over repeated updates. Ablation analysis showed measurable degradation when reflective modules were removed, and robustness tests confirmed stable retention under noise. These results demonstrate that structured reflection enables durable memory consolidation and controlled adaptability for long-context agentic reasoning.

References
  1. Albert Albesa-Gonz´alez and Claudia Clopath. From episodes to concepts and back: Semantic representations in episodic memory enhance recall, replay, and compositional consolidation. bioRxiv, pages 2025–10, 2025.
  2. Yihao Ang, Yifan Bao, Lei Jiang, Jiajie Tao, Anthony KH Tung, Lukasz Szpurch, and Hao Ni. Structured agentic workflows for financial time-series modelling with llms and reflective feedback. In Proceedings of the 6th ACM International Conference on AI in Finance, pages 924–932, 2025.
  3. Felix Ashworth, Eric Watson, Blaine Kingsley, Travis Connor, Andrew Scolto, and Benedict Sutherlands. Symbolrooted cascade propagation in contextual memory routing for large language models. researchgate.net, 2025.
  4. Muhammad Azam, Tanveer Rafiq, Falak Gul Naz, Maria Ghafoor, Maher Un Nisa, and Hammad Malik. A novel model of narrative memory for conscious agents. International Journal of Information Systems and Computer Technologies, 3(1):12–22, 2024.
  5. Andrej Bicanski. Breaking the chains: Toward a neural-level account of episodic memory. Psychological Review, 2025.
  6. UweMBorghoff, Paolo Bottoni, and Remo Pareschi. Beyond prompt chaining: The tb-cspn architecture for agentic ai. Future Internet, 17(8):363, 2025.
  7. Yassine Boudjemaa and Karim Belkacem. Enhancing knowledge acquisition and retention through adaptive learning by reading systems with personalized content delivery. Studies in Knowledge Discovery, Intelligent Systems, and Distributed Analytics, 14(11):1–12, 2024.
  8. Markus J Buehler. Agentic deep graph reasoning yields selforganizing knowledge networks. Journal of Materials Research, 40(15):2204–2242, 2025.
  9. Illia Fedorin. Virtual ppg reconstruction from accelerometer data via adaptive denoising and cross-modal fusion. Information Fusion, page 103781, 2025.
  10. Carmen Fern´andez Wilt. The development of episodic memory in early childhood education: Theoretical models and pedagogical implications. 2024.
  11. Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, et al. Enabling self-improving agents to learn at test time with humanin- the-loop guidance. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1625–1653, 2025.
  12. Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, and Ping Luo. Hiagent: Hierarchical working memory management for solving long-horizon agent tasks with large language model. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 32779–32798, 2025.
  13. Zixi Jia, Qinghua Liu, Hexiao Li, Yuyan Chen, and Jiqiang Liu. Evaluating the long-term memory of large language models. In Findings of the Association for Computational Linguistics: ACL 2025, pages 19759–19777, 2025.
  14. Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. Hipporag: Neurobiologically inspired long-term memory for large language models. Advances in Neural Information Processing Systems, 37:59532–59569, 2024.
  15. Siu-Cheung Kong and Yin Yang. A human-centered learning and teaching framework using generative artificial intelligence for self-regulated learning development through domain knowledge learning in k–12 settings. IEEE Transactions on Learning Technologies, 17:1562–1573, 2024.
  16. Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Jonghwan Hyeon, and Ho-Jin Choi. Dialogcc: An automated pipeline for creating high-quality multi-modal dialogue dataset. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1938–1963, 2024.
  17. Francois Leonardi, Patrick Feldman, Matthew Almeida, William Moretti, and Charles Iverson. Contextual feature drift in large language models: An examination of adaptive retention across sequential inputs. files.osf.io, 2024.
  18. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K¨uttler, Mike Lewis, Wen-tau Yih, Tim Rockt¨aschel, et al. Retrievalaugmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459– 9474, 2020.
  19. Jiajun Li, Yixuan Zhang, Yuhan Xu, Wei Zhao, Zhiyuan Liu, and Maosong Sun. DuLeMon: A Large-scale Chinese Longterm Memory Dialogue Dataset for Conversational Agents. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pages 13245–13259. Association for Computational Linguistics, 2023.
  20. Zongxi Li, Zijian Wang, Weiming Wang, Kevin Hung, Haoran Xie, and Fu Lee Wang. Retrieval-augmented generation for educational application: A systematic survey. Computers and Education: Artificial Intelligence, page 100417, 2025.
  21. Xuechen Liang, Meiling Tao, Yinghui Xia, Jianhui Wang, Kun Li, YijinWang, Yangfan He, Jingsong Yang, Tianyu Shi, Yuantao Wang, et al. Sage: Self-evolving agents with reflective and memory-augmented abilities. Neurocomputing, page 130470, 2025.
  22. Mohammad Madani, Valentina Lacivita, Yongwoo Shin, and Anna Tarakanova. Accelerating materials property prediction via a hybrid transformer graph framework that leverages four body interactions. npj Computational Materials, 11(1):15, 2025.
  23. Zainab Maqsood, Madiha Sajjad, and Raheela Yasmin. Effect of feedback-integrated reflection, on deep learning of undergraduate medical students in a clinical setting. BMC Medical Education, 25(1):66, 2025.
  24. Kathleen B McDermott and Henry L Roediger III. Memory (encoding, storage, retrieval). Understanding Biological Behavior 2nd Edition, 2025.
  25. Siyuan Meng, Jie Zhou, Xuxin Chen, Yufei Liu, Fengyuan Lu, and Xinli Huang. Structure-information-based reasoning over the knowledge graph: A survey of methods and applications. ACM Transactions on Knowledge Discovery from Data, 18(8):1–42, 2024.
  26. Ibomoiye Domor Mienye, Theo G Swart, and George Obaido. Recurrent neural networks: A comprehensive review of architectures, variants, and applications. Information, 15(9):517, 2024.
  27. Narcisa Roxana Mos¸teanu. Adapting to the unpredictable: Building resilience for business continuity in an everchanging landscape. European Journal of Theoretical and Applied Sciences, 2(1):444–457, 2024.
  28. Aila Naderbagi, Victoria Loblay, Iqthyer Uddin Md Zahed, Mahalakshmi Ekambareshwar, Adam Poulsen, Yun JC Song, Laura Ospina-Pinillos, Michael Krausz, Mostafa Mamdouh Kamel, Ian B Hickie, et al. Cultural and contextual adaptation of digital health interventions: narrative review. Journal of medical Internet research, 26:e55130, 2024.
  29. Geoff Norman, Thierry Pelaccia, Peter Wyer, and Jonathan Sherbino. Dual process models of clinical reasoning: the central role of knowledge in diagnostic expertise. Journal of Evaluation in Clinical Practice, 30(5):788–796, 2024.
  30. Mulyadi Nur and Fatmawati Sabur. Development of teaching materials and harmonized semester learning plan for the aircraft basic workshop theory course through learnercentered instructional design in indonesian aviation polytechnics. Journal La Edusci, 6(2):284–307, 2025.
  31. Tony J Prescott and Peter F Dominey. Synthesizing the temporal self: robotic models of episodic and autobiographical memory. Philosophical Transactions B, 379(1913):20230415, 2024.
  32. Harkiran Sahota and Adam Kłodowski. Knowledge representation and reasoning in the context of automated production planning. Journal of Intelligent Manufacturing, pages 1–20, 2025.
  33. Qingran Su, Xingze Li, Yuming Ren, Ruinan Qiu, Chunming Hu, and Yongfeng Yin. Attention transfer reinforcement learning for test case prioritization in continuous integration. Applied Sciences, 15(4):2243, 2025.
  34. Danail Valov, Usman Ahmad, and Adrian Lipa. The recursive brain toward a unified symbolic biological and topological model of human cognition. DOI http://dx. doi. org/10.13140/RG, 2(24485.00481), 2025.
  35. Haotian Wang. Behavioral decision-making of mobile robots simulating the memory consolidation mechanism of human brain. Adaptive Behavior, 33(2):135–149, 2025.
  36. Hua Wu, Haotian Hong, Jiayu Mao, Zhexun Yin, Yanxiong Wu, Xiaojing Bai, Li Sun, Mengyang Pu, Juncheng Liu, and Yihuan Li. Forging robust cognition resilience in large language models: The self-correction reflection paradigm against input perturbations. Applied Sciences, 15(9):5041, 2025.
  37. Yosif Zaki and Denise J Cai. Memory engram stability and flexibility. Neuropsychopharmacology, 50(1):285–293, 2025.
  38. Fuwei Zhang, Zhao Zhang, Fuzhen Zhuang, Yu Zhao, Deqing Wang, and Hongwei Zheng. Temporal knowledge graph reasoning with dynamic memory enhancement. IEEE Transactions on Knowledge and Data Engineering, 36(11):7115– 7128, 2024.
  39. Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, and Sercan Arik. Chain of agents: Large language models collaborating on long-context tasks. Advances in Neural Information Processing Systems, 37:132208–132237, 2024.
  40. Zeyu Zhang, Quanyu Dai, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. A survey on the memory mechanism of large language modelbased agents. ACM Transactions on Information Systems, 43(6):1–47, 2025.
  41. Qinghua Zheng, Huan Liu, Xiaoqing Zhang, Caixia Yan, Xiangyong Cao, Tieliang Gong, Yong-Jin Liu, Bin Shi, Zhen Peng, Xiaocen Fan, et al. Machine memory intelligence: Inspired by human memory mechanisms. Engineering, 2025.
  42. Wanjun Zhong, Lianghong Guo, Qiqi Gao, and Yanlin Wang. Memorybank: Enhancing large language models with longterm memory. arXiv preprint arXiv:2305.10250, 2023.
Index Terms

Computer Science
Information Sciences

Keywords

Automated AI agents Adversarial Context Injection Model Context Protocol Robustness Anomaly Detection Defense Mechanisms

Powered by PhDFocusTM