The DOI matches its Crossref record; 206 of the 206 references it cites were found in a registry or an index.
Lifelong Learning of Large Language Model Based Agents: A Roadmap
Abstract
Lifelong learning, also known as continual or incremental learning, is a crucial component for advancing Artificial General Intelligence (AGI) by enabling systems to continuously adapt in dynamic environments. While large language models (LLMs) have demonstrated impressive capabilities in natural language processing, existing LLM agents are typically designed for static systems and lack the ability to adapt over time in response to new challenges. This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents. We categorize the core components of these agents into three modules: the perception module for multimodal input integration, the memory module for storing and retrieving evolving knowledge, and the action module for grounded interactions with the dynamic environment. We highlight how these pillars collectively enable continuous adaptation, mitigate catastrophic forgetting, and improve long-term performance. This survey provides a roadmap for researchers and practitioners working to develop lifelong learning capabilities in LLM agents, offering insights into emerging trends, evaluation metrics, and application scenarios.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Empirically, this kind of reviewer setup has been shown to reduce hallucinations in LLM-generated answers [47,48].”
From A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis (2026) · cites this paper as [47]
In the citing paper
“Zheng et al. (2025) outlined strategies for incorporating lifelong learning into agent architecture by dividing the system into a perception module (to handle new modalities), a memory module (to accumulate evolving knowledge), and an action module (to adapt behaviors) [47].”
From A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis (2026) · cites this paper as [47]
In the citing paper
“An agent adopting a poorly designed memory architecture can suffer from factual contradictions, catastrophic forgetting, or unacceptable latencies during continuous execution [6, 38].”
From Are We Ready For An Agent-Native Memory System? (2026) · cites this paper as [38]
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.09388 · Cited by 17,283
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899 · cited 1×
“In industrial applications such as robotics and autonomous vehicles, deep lifelong learning methods—including Elastic Weight Consolidation (EWC) [36]—have enabled systems to adapt to new tasks while preserving previously acquired skills, thereby supporting long-term autonomy and operational…”
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Some Studies in Machine Learning Using the Game of Checkers
Samuel, A. L. (1959) · IBM Journal of Research and Development · doi:10.1147/rd.33.0210 · Cited by 4,443
Knowledge Distillation: A Survey
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01453-z · Cited by 3,931 · cited 1×
“Additionally, by combining knowledge distillation [63], [64], [65] and regularization methods, some studies [62], [66], [67], [68] leverage the high-performance capability of the teacher model in one modality to transfer its knowledge to the student model through constraint-based mapping.”
Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem
McCloskey, M., & Cohen, N. J. (1989) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60536-8 · Cited by 3,770 · cited 3×
“Whilehumanscannaturallyintegratenewknowledge whileretainingtheold,currentAIsystemsfacetwomainchal-lengesinlifelonglearning: catastrophic forgetting [6] and loss of plasticity [7], [8].”
Sallam, M. (2023) · Healthcare · doi:10.3390/healthcare11060887 · Cited by 3,126 · cited 1×
“Restrictions apply. safety-critical domains such as healthcare [186] or autonomous systems.”
Continual lifelong learning with neural networks: A review
Parisi, G. I., Kemker, R., Part, J. L., Kanan, C., & Wermter, S. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.01.012 · Cited by 3,117
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
Hong, S., Zhuge, M., Chen, J., Zheng, X., Cheng, Y., Zhang, C., Wang, J., Wang, Z., Yau, S. K. S., Lin, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.00352 · Cited by 2,825
Catastrophic forgetting in connectionist networks
French, R. (1999) · Trends in Cognitive Sciences · doi:10.1016/s1364-6613(99)01294-2 · Cited by 2,311 · cited 1×
“Ontheotherhand,Cross-ModalKnowledgeTransferinvolves applying knowledge from one modality to improve performance on tasks in another modality [60], [61], [62], [63].”
Foundation models for generalist medical artificial intelligence
Moor, M., Banerjee, O., Abad, Z. S. H., Krumholz, H. M., Leskovec, J., Topol, E. J., & Rajpurkar, P. (2023) · Nature · doi:10.1038/s41586-023-05881-4 · Cited by 2,028 · cited 1×
“In education [171], [172] and healthcare [173], agents adaptively integrate new knowledge to provide personalized teaching and decision support in safety-critical contexts.”
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · cited 3×
“Unlike standard LLMs, which process input text and generate output based on prior training, LLM agents [13], [14] are autonomous entities capable of interacting with their environment.”
A Survey on Large Language Model based Autonomous Agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.11432 · Cited by 1,925
A Continual Learning Survey: Defying Forgetting in Classification Tasks
Delange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3057446 · Cited by 1,647 · cited 1×
“L IFELONG learning [1], [2], also known as continual or incremental learning [3], [4], has become a key focus in the development of intelligent systems.”
A continual learning survey: Defying forgetting in classification tasks
De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G., & Tuytelaars, T. (2019) · arXiv · doi:10.48550/arxiv.1909.08383 · Cited by 1,647
Expel: LLM agents are experiential learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29936 · Cited by 1,451
Continual Learning with Deep Generative Replay
Shin, H., Lee, J. K., Kim, J., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1705.08690 · Cited by 1,385
End-to-End Incremental Learning
Castro, F. M., Marín-Jiménez, M. J., Guil, N., Schmid, C., & Alahari, K. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01258-8_15 · Cited by 1,184 · cited 1×
“Data replay mainly involves two types of replay techniques, experience replay [104], [105] and generative replay [106], [107].”
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., & Narasimhan, K. (2023) · arXiv · doi:10.48550/arxiv.2305.10601 · Cited by 1,158
Self-citationToolformer: Language Models Can Teach Themselves to Use Tools
Schick, T., Dwivedi-Yu, J., Dessì, R., Raileanu, R., Lomeli, M., Zettlemoyer, L., Cancedda, N., & Scialom, T. (2023) · arXiv · doi:10.48550/arxiv.2302.04761 · Cited by 1,150
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113 · cited 4×
“We include a detailed summary of existing surveys in Appendix A, available in the online supplemental material.”
InfluentialReflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 1×
“Reflexion [159] is one of the most representative studies.”
The Rise and Potential of Large Language Model Based Agents: A Survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.07864 · Cited by 972 · cited 4×
“This division follows the framework introduced in prior work [14], with one notable difference: rather than retaining the “Brain” module, we adopt a “Memory” module as proposed in [14], offering clearer functionality and improved modularity.”
InfluentialThe rise and potential of large language model based agents: a survey
Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., et al. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970
Retrieval-Augmented Generation for Large Language Models: A Survey
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., & Wang, H. (2023) · arXiv · doi:10.48550/arxiv.2312.10997 · Cited by 876
Catastrophic forgetting, rehearsal and pseudorehearsal
ROBINS, A. (1995) · Connection Science · doi:10.1080/09540099550039318 · Cited by 833 · cited 1×
“These challenges form the stability-plasticity dilemma [9].”
Cognitive Architectures for Language Agents
Sumers, T. R., Yao, S., Narasimhan, K., & Griffiths, T. L. (2023) · arXiv · doi:10.48550/arxiv.2309.02427 · Cited by 798
Wang, Z., Cai, S., Chen, G., Liu, A., Ma, X. (., & Liang, Y. (2023) · neural information processing systems · doi:10.52202/075280-1480 · Cited by 726
Haleem, A., Javaid, M., & Singh, R. P. (2022) · BenchCouncil Transactions on Benchmarks, Standards and Evaluations · doi:10.1016/j.tbench.2023.100089 · Cited by 694
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
Rafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2338 · Cited by 686
Multi-Agent Collaboration Mechanisms: A Survey of LLMs
Tran, K.-T., Dao, D., Nguyen, M.-D., Pham, Q.-V., O'Sullivan, B., & Nguyen, H. D. (2025) · arXiv · doi:10.48550/arxiv.2501.06322 · Cited by 680
Unlocking the Power of ChatGPT: A Framework for Applying Generative AI in Education
Su (苏嘉红), J., & Yang (杨伟鹏), W. (2023) · ECNU Review of Education · doi:10.1177/20965311231168423 · Cited by 625 · cited 1×
“In education [171], [172] and healthcare [173], agents adaptively integrate new knowledge to provide personalized teaching and decision support in safety-critical contexts.”
ReAct: Synergizing Reasoning and Acting in Language Models
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022) · arXiv · doi:10.48550/arxiv.2210.03629 · Cited by 608
Self-citationMixture of experts: a literature survey
Masoudnia, S., & Ebrahimpour, R. (2014) · Artificial Intelligence Review · doi:10.1007/s10462-012-9338-y · Cited by 561 · cited 1×
“The MoE [69] module enables PathWeave [70] to introduce a framework that integrates single-modal and cross-modal adapters for efficient modality adaptation.”
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Gou, Z., Shao, Z., Gong, Y., Shen, Y., Yang, Y., Duan, N., & Chen, W. (2023) · arXiv · doi:10.48550/arxiv.2305.11738 · Cited by 561
Cross Modal Distillation for Supervision Transfer
Gupta, S., Hoffman, J., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.309 · Cited by 530 · cited 1×
“The detailed discussions areprovidedinAppendixQ,availableintheonlinesupplemental material.”
Learning to Compress Prompts with Gist Tokens
Mu, J., Li, X. (., & Goodman, N. D. (2023) · neural information processing systems · doi:10.52202/075280-0848 · Cited by 530
Three scenarios for continual learning
van de Ven, G. M., & Tolias, A. S. (2019) · Lirias · doi:10.48550/arxiv.1904.07734 · Cited by 523
Memory Replay GANs: learning to generate images from new categories without forgettingPreprint
Wu, C., Herranz, L., Liu, X., wang, Y., van de Weijer, J., & Raducanu, B. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02058 · Cited by 483
Large Language Model Alignment: A SurveyPreprint
Shen, T., Jin, R., Huang, Y., Liu, C., Dong, W., Guo, Z., Wu, X., Liu, Y., & Xiong, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.15025 · Cited by 470
Chen, Z., & Liu, B. (2018) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01581-6 · Cited by 466
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
Wang, N., Peng, Z., Que, H., Liu, J., Zhou, W., Wu, Y., Guo, H., Gan, R., Ni, Z., Yang, J. J., et al. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.878 · Cited by 435
Perceiver: General Perception with Iterative Attention
Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., & Carreira, J. (2021) · arXiv · doi:10.48550/arxiv.2103.03206 · Cited by 414
Yu, Y., Yao, Z., Li, H., Deng, Z., Jiang, Y., Cao, Y., Chen, Z., Suchow, J. W., Cui, Z., Liu, R., et al. (2024) · neural information processing systems · doi:10.52202/079017-4354 · Cited by 398
Self-citationClass-Incremental Learning: A Survey
Zhou, D.-W., Wang, Q.-W., Qi, Z.-H., Ye, H.-J., Zhan, D.-C., & Liu, Z. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3429383 · Cited by 376
Wang, J., Xu, H., Jia, H., Zhang, X., Yan, M., Shen, W., Zhang, J., Huang, F., & Sang, J. (2024) · neural information processing systems · doi:10.52202/079017-0088 · Cited by 345
SMIL: Multimodal Learning with Severely Missing Modality
Ma, M., Ren, J., Zhao, L., Tulyakov, S., Wu, C., & Peng, X. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i3.16330 · Cited by 332 · cited 1×
“Somestudies [71], [72], [73] have explored ways to predict the missing modality by utilizing available modality information.”
Continual Learning for Large Language Models: A SurveyPreprint
Wu, T., Luo, L., Li, Y.-F., Pan, S., Vu, T.-T., & Haffari, G. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.01364 · Cited by 328
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
Akbari, H., Yuan, L., Qian, R., Chuang, W.-H., Chang, S., Cui, Y., & Gong, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.11178 · Cited by 326
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
Hao, S., Liu, T., Wang, Z., & Hu, Z. (2023) · neural information processing systems · doi:10.52202/075280-1988 · Cited by 324
Mitigating the Alignment Tax of RLHF
Lin, Y. B., Lin, H., Xiong, W., Diao, S., Liu, J., Zhang, J., Pan, R., Wang, H., Hu, W., Zhang, H., et al. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.35 · Cited by 321
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
Kazakos, E., Nagrani, A., Zisserman, A., & Damen, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00559 · Cited by 302 · cited 2×
“Ontheotherhand,Cross-ModalKnowledgeTransferinvolves applying knowledge from one modality to improve performance on tasks in another modality [60], [61], [62], [63].”
Mapping Natural Language Instructions to Mobile UI Action Sequences
Li, Y., He, J., Zhou, X., Zhang, Y., & Baldridge, J. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.729 · Cited by 288 · cited 1×
“This capability makes the agent more agile and effective in complex and changing environments, continually learning and evolving from interactions.”
Nguyen (2022) · doi:10.1145/3453476 · Cited by 286 · cited 1×
“A basic form applies OCR [42] to extract visible text.”
OmniParser for Pure Vision Based GUI AgentPreprint
Lü, Y., Yang, J., Shen, Y., & Awadallah, A. H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.00203 · Cited by 286
Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities
Zhao, J., Li, R., & Jin, Q. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.203 · Cited by 275 · cited 1×
“Somestudies [71], [72], [73] have explored ways to predict the missing modality by utilizing available modality information.”
Learning to Speak and Act in a Fantasy Text Adventure Game
Urbanek, J., Fan, A., Karamcheti, S., Jain, S., Humeau, S., Dinan, E., Rocktäschel, T., Kiela, D., Szlam, A. D., & Weston, J. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1062 · Cited by 266 · cited 1×
“…testbeds of this type: LLM agents can perceive their surroundings through textual mediums [49], [50], [51], recognizing elements such as characters, time, location, events, and emotions [52], and can perform corresponding actions based on feedback from these elements using textual instructions.”
Compressing Context to Enhance Inference Efficiency of Large Language Models
Li, Y., Dong, B., Guerin, F., & Lin, C. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.391 · Cited by 253
MemoryBank: Enhancing Large Language Models with Long-Term Memory
Zhong, W., Guo, L., Gao, Q., Ye, H., & Wang, Y. (2023) · arXiv · doi:10.48550/arxiv.2305.10250 · Cited by 253
Generative Feature Replay For Class-Incremental Learning
Liu, X., Wu, C., Menta, M., Herranz, L., Raducanu, B., Bagdanov, A. D., Jui, S., & van de Weijer, J. (2020) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00121 · Cited by 233 · cited 1×
“Feature replay [108] is a strategy that focuses on preserving thedistributionoffeaturesratherthanthedataitself,whichoffers significantadvantagesintermsofefficiencyandprivacy.”
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
Zheng, Z., Ma, M., Wang, K., Qin, Z., Yue, X., & You, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01752 · Cited by 231 · cited 2×
“The detailed discussions areprovidedinAppendixQ,availableintheonlinesupplemental material.”
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
Yuan, S., Song, K., Chen, J., Tan, X., Shen, Y., Ren, K., Li, D., & Yang, D. (2025) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2025.naacl-long.44 · Cited by 231
You Only Look at Screens: Multimodal Chain-of-Action Agents
Zhang, Z., & Zhang, A. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.186 · Cited by 228
Voyager: An Open-Ended Embodied Agent with Large Language Models
Wang, G., Xie, Y., Jiang, Y., Mandlekar, A., Xiao, C., Zhu, Y., Fan, L., & Anandkumar, A. (2023) · arXiv · doi:10.48550/arxiv.2305.16291 · Cited by 222
Multi-Modal Learning with Missing Modality via Shared-Specific Feature Modelling
Wang, H., Chen, Y., Ma, C., Avery, J., Hull, L., & Carneiro, G. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01524 · Cited by 216 · cited 1×
“Additionally, other research [74], [75] focuses on improving input data representations by learning both shared and modality-specific features.”
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt OptimizationPreprint
Wang, X., Li, C., Wang, Z., Bai, F., Luo, H., Zhang, J., Jojić, N., Xing, E. P., & Hu, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.16427 · Cited by 211
Self-citationContinual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks
Shaheen, K., Hanif, M. A., Hasan, O., & Shafique, M. (2022) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-022-01603-6 · Cited by 202
CogAgent: A Visual Language Model for GUI Agents
Hong, W., Wang, W., Lv, Q., Xu, J., Yu, W., Ji, J., Wang, Y., Wang, Z., Dong, Y., Ding, M., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01354 · Cited by 202 · cited 1×
“More advanced methods [43], [44], [45], [46], [47], [48] combine OCR with coordinate grounding, enabling agents to localize and interact with specific icons or regions on the screen.”
Omnivore: A Single Model for Many Visual Modalities
Girdhar, R., Singh, M., Ravi, N., van der Maaten, L., Joulin, A., & Misra, I. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01563 · Cited by 196 · cited 1×
“Some studies [57], [58], [59] have explored Modality-Agnostic Models, which can perceive any modality as input.”
Distribution-Consistent Modal Recovering for Incomplete Multimodal Learning
Wang, Y., Cui, Z., & Li, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02013 · Cited by 183 · cited 1×
“12.”
ExpeL: LLM Agents Are Experiential Learners
Zhao, A., Huang, D., Xu, Q., Lin, M., Liu, Y.-J., & Huang, G. (2023) · arXiv · doi:10.48550/arxiv.2308.10144 · Cited by 179
Towards Lifelong Learning of Large Language Models: A Survey
Zheng, J., Qiu, S., Shi, C., & Ma, Q. (2025) · ACM Computing Surveys · doi:10.1145/3716629 · Cited by 178 · cited 7×
“Continualknowledgeeditingupdates theunderstandingofthemodelthroughknowledgetriplets-like (head_entity, relation, tail_entity) to ensure that the model is able to adjust its knowledge base when it discovers that prior knowledge is outdated or when it encounters new information [1].”
InfluentialSelf-citationLoss of plasticity in deep continual learning
Dohare, S., Hernandez-Garcia, J. F., Lan, Q., Rahman, P., Mahmood, A. R., & Sutton, R. S. (2024) · Nature · doi:10.1038/s41586-024-07711-7 · Cited by 172 · cited 1×
“Whilehumanscannaturallyintegratenewknowledge whileretainingtheold,currentAIsystemsfacetwomainchal-lengesinlifelonglearning: catastrophic forgetting [6] and loss of plasticity [7], [8].”
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
Shen, W., Li, C., Chen, H., Yan, M. G., Quan, X., Chen, H., Zhang, J., & Huang, F. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.929 · Cited by 170
Self-citationLLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Jiang, H., Wu, Q., Lin, C.-Y., Yang, Y., & Qiu, L. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.825 · Cited by 168
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
Jiang, H., Wu, Q., Lin, C.-Y., Yang, Y., & Qiu, L. (2023) · arXiv · Cited by 168
AutoGLM: Autonomous Foundation Agents for GUIsPreprint
Liu, X., Qin, B., Liang, D., Dong, G., Lai, H., Zhang, H., Zhao, H., Iong, I. L., Sun, J., Wang, J., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.00820 · Cited by 156
A Survey on the Memory Mechanism of Large Language Model based Agents
Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., & Wen, J.-R. (2024) · arXiv · doi:10.48550/arxiv.2404.13501 · Cited by 149 · cited 1×
“The memory systems [187] that enable lifelong learning also pose serious privacy threats.”
Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory
Chen, X., Luo, D., Chen, X., Liu, L., Zhao, D., & Yan, R. (2023) · neural information processing systems · doi:10.52202/075280-1899 · Cited by 146
Legal Prompting: Teaching a Language Model to Think Like a LawyerPreprint
Yu, F., Quartey, L., & Schilder, F. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.01326 · Cited by 141
Character-LLM: A Trainable Agent for Role-Playing
Shao, Y., Li, L., Dai, J., & Qiu, X. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.814 · Cited by 140
MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis
Lin, R., & Hu, H. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00628 · Cited by 134 · cited 1×
“12.”
(2023) · doi:10.52202/075280-1220 · Cited by 134
Sentence Embedding Alignment for Lifelong Relation Extraction
Wang, H., Xiong, W., Yu, M., Guo, X., Chang, S., & Wang, W. Y. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1086 · Cited by 127 · cited 1×
“In this subsection, we follow the experimental setting of LifelongAgentBench and evaluate the performance of representative LLM agents on LifelongAgentBench [162].”
Retrieval-Generation Synergy Augmented Large Language Models
Feng, Z., Feng, X., Zhao, D., Yang, M., & Qin, B. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448015 · Cited by 117 · cited 1×
“At work, they improve search, recommendation, and knowledge management by dynamically organizing and retrieving information [145], [155], [163], [164].”
Preserving and combining knowledge in robotic lifelong reinforcement learning
Meng, Y., Bing, Z., Yao, X., Chen, K., Huang, K., Gao, Y., Sun, F., & Knoll, A. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-00983-2 · Cited by 117 · cited 1×
“These challenges are not unique to supervised learning settings; they also appear prominently in reinforcement learning (RL), where agents must retain past knowledge while learning from sequential interactions [34].”
VisualAgentBench: Towards Large Multimodal Models as Visual Foundation AgentsPreprint
Liu, X., Zhang, T., Gu, Y., Iong, I. L., Xu, Y., Song, X., Zhang, S., Lai, H., Liu, X., Zhao, H., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.06327 · Cited by 117
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Furuta, H., Lee, K.-H., Nachum, O., Matsuo, Y., Faust, A., Gu, S. S., & Gur, I. (2023) · arXiv · doi:10.48550/arxiv.2305.11854 · Cited by 115
Parallel Context Windows for Large Language Models
Ratner, N., Levine, Y., Belinkov, Y., Ram, O., Magar, I., Abend, O., Karpas, E., Shashua, A., Leyton-Brown, K., & Shoham, Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.352 · Cited by 111 · cited 1×
“There are two main approaches for long text processing, context selection [88], [89] and context aggregation [90], [91].”
The Oscars of AI Theater: A Survey on Role-Playing with Language ModelsPreprint
Chen, N., Wang, Y. S., Deng, Y., & Li, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.11484 · Cited by 108
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Yao, S., Chen, H., Yang, J., & Narasimhan, K. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1508 · Cited by 107
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Yao, S., Chen, H., Yang, J., & Narasimhan, K. (2022) · arXiv · doi:10.48550/arxiv.2207.01206 · Cited by 107
Xia, Y., Shenoy, M., Jazdi, N., & Weyrich, M. (2023) · 2023 IEEE 28th International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa54631.2023.10275362 · Cited by 103
A Survey of Multi-Agent Systems on Distributed Formation Control
Liu, Y., Liu, J., He, Z., et al. (2023) · Unmanned Systems · doi:10.1142/s2301385024500274 · Cited by 102
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language ModelsPreprint
Zhu, D., Sun, Z., Li, Z., Shen, T., Yan, K., Ding, S., Kuang, K., & Wu, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.12048 · Cited by 102
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
Long, L., He, Y., Ye, W., Pan, Y., Lin, Y., Li, H., Zhao, J., & Li, W. (2025) · arXiv · doi:10.48550/arxiv.2508.09736 · Cited by 102
Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language ModelsPreprint
Li, L., Chen, Z., Chen, G., Zhang, Y., Su, Y., Xing, E. P., & Zhang, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.12563 · Cited by 97
Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs
Cui, Y., Wang, Y., Sun, Z., Liu, W., Jiang, Y., Han, K., & Hu, W. P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25539 · Cited by 93
VQACL: A Novel Visual Question Answering Continual Learning Setting
Zhang, X., Zhang, F., & Xu, C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01831 · Cited by 91 · cited 1×
“This fine-tuning not only enhances the responses of the agents to new commands but also allows them to absorb and integrate new information without forgetting previous knowledge through continuous learning.”
LASER: LLM Agent with State-Space Exploration for Web NavigationPreprint
Ma, K., Zhang, H., Wang, H., Pan, X., Yu, D., & Yu, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.08172 · Cited by 90
Self-citationCompressing Context to Enhance Inference Efficiency of Large Language Models
Li, Y., Dong, B., Lin, C., & Guerin, F. (2023) · arXiv · Cited by 88 · cited 1×
“The techniques for prompt compression are classified mainly into two categories: soft compression [84], [85] and hard compression [86], [87].”
Towards Continual Knowledge Graph Embedding via Incremental Distillation
Liu, J., Ke, W., Wang, P., Shang, Z., Gao, J., Li, G., Ji, K., & Liu, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i8.28722 · Cited by 85 · cited 1×
“To tackle this, continual knowledge graph embedding (CKGE) has emerged, using incremental learning to efficiently update and integrate new knowledge [114] while preserving existing knowledge [115], [116].”
Online Learned Continual Compression with Adaptive Quantization ModulesPreprint
Caccia, L., Belilovsky, E., Caccia, M., & Pineau, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.08019 · Cited by 84
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
Sarch, G. H., Jang, L., Tarr, M. J., Cohen, W. W., Marino, K., & Fragkiadaki, K. (2024) · neural information processing systems · doi:10.52202/079017-2418 · Cited by 83 · cited 2×
“The first category involves storing the agent’s trajectory in a database after it completes a task successfully [145], [154].”
Repetitive Activity Counting by Sight and Sound
Zhang, Y., Shao, L., & Snoek, C. G. M. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01385 · Cited by 82
Knowledge Editing for Large Language Models: A Survey
Wang, S., Zhu, Y., Liu, H., Zheng, Z., Chen, C., & Li, J. (2025) · ACM Computing Surveys · doi:10.1145/3698590 · Cited by 79
AgentBench: Evaluating LLMs as Agents
Liu, X., Yu, H., Zhang, H., Xu, Y., Lei, X., Lai, H., Gu, Y., Ding, H., Men, K., Yang, K., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.03688 · Cited by 79
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
Wang, B., Fang, H., Eisner, J. M., Durme, B. V., & Su, Y. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.570 · Cited by 77
Qin, Y., Liang, S., Ye, Y., Zhu, K., Yan, L., Lu, Y., Lin, Y., Cong, X., Tang, X., Qian, B., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.16789 · Cited by 71
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
Cheng, K., Sun, Q., Chu, Y., Xu, F., YanTao, L., Zhang, J., & Wu, Z. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.505 · Cited by 70
WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing
Hu, C., Cao, P., Chen, Y., Kang, L., & Zhao, J. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.207 · Cited by 70
Continual Instruction Tuning for Large Multimodal Models
He, J., Guo, H., Zhu, K., Tang, M., & Wang, J. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3671616 · Cited by 68 · cited 1×
“Weight regularization [76], [77] applies penalty terms to model weights to restrict their updates when learning new tasks.”
Bring Evanescent Representations to Life in Lifelong Class Incremental Learning
Toldo, M., & Özay, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01623 · Cited by 65 · cited 1×
“RER[109]takesadirectapproachtoestimatethe shiftsinrepresentation,allowingfortheupdatingofpreserved oldfeaturestoalignwithnewones.”
ChatLLM network: More brains, more intelligence
Hao, R., Hu, L., Qi, W., Wu, Q., Zhang, Y., & Nie, L. (2025) · AI Open · doi:10.1016/j.aiopen.2025.01.001 · Cited by 65
Long Time No See! Open-Domain Conversation with Long-Term Persona Memory
Xu, X., Gou, Z., Wu, W., Niu, Z.-Y., Wu, H., Wang, H., & Wang, S. (2022) · arXiv · doi:10.48550/arxiv.2203.05797 · Cited by 65
Recent Advances of Multimodal Continual Learning: A Comprehensive Survey
Yu, D., Zhang, X., Chen, Y., Liu, A., Zhang, Y., Yu, P. S., & King, I. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3658485 · Cited by 63 · cited 1×
“In order to summarize the research in this area, researchers have written a large number of surveys [24], [25], [26].”
Self-citationDisentangle-based Continual Graph Representation Learning
Kou, X., Lin, Y., Liu, S., Li, P., Zhou, J., & Zhang, Y. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.237 · Cited by 62 · cited 1×
“CurrentCKGEmethodsarebroadlycategorizedintothree types:replay-basedapproach[117],[118],regularization-based approach[116],[119],andarchitecture-basedapproach[114], [120].”
Feng, Q., Li, W., Lin, T., & Chen, X. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00395 · Cited by 62 · cited 2×
“Ontheotherhand,Cross-ModalKnowledgeTransferinvolves applying knowledge from one modality to improve performance on tasks in another modality [60], [61], [62], [63].”
Adapting Language Models to Compress Contexts
Chevalier, A., Wettig, A., Ajith, A., & Chen, D. (2023) · Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2023.emnlp-main.232 · Cited by 59
Adapting Language Models to Compress Contexts
Chevalier, A., Wettig, A., Ajith, A., & Chen, D. (2023) · arXiv · Cited by 59 · cited 1×
“We begin by outlining the key challenges lifelong LLM agents face in executing these grounding actions, then explore corresponding solutions under different environmental contexts.”
Wang, Z., Cai, S., Chen, G., Liu, A., Ma, X., & Liang, Y. (2023) · arXiv · doi:10.48550/arxiv.2302.01560 · Cited by 55
Zhu, H., Wei, Y., Liang, X., Zhang, C., & Zhao, Y. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02034 · Cited by 53 · cited 2×
“Additionally, by combining knowledge distillation [63], [64], [65] and regularization methods, some studies [62], [66], [67], [68] leverage the high-performance capability of the teacher model in one modality to transfer its knowledge to the student model through constraint-based mapping.”
A-Mem: Agentic Memory for LLM Agents
Xu, W., Liang, Z., Mei, K., Gao, H., Tan, J., & Zhang, Y. (2025) · Advances in Neural Information Processing Systems 38 · doi:10.52202/085713-0593 · Cited by 51
Long-Span Summarization via Local Attention and Content Selection
Manakul, P., & Gales, M. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.470 · Cited by 50 · cited 1×
“There are two main approaches for long text processing, context selection [88], [89] and context aggregation [90], [91].”
VisualWebArena: evaluating multimodal agents on realistic visual web tasks
Koh, J. Y., Lo, R., Jang, L., Duvvur, V., Lim, M., Huang, P.-Y., Neubig, G., Zhou, S., Salakhutdinov, R., & Fried, D. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.50 · Cited by 50
EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Guo, Q., Wang, R., Guo, J., Li, B., Song, K., Tan, X., Liu, G., Bian, J., & Yang, Y. (2023) · arXiv · doi:10.48550/arxiv.2309.08532 · Cited by 50
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Lin, B. Y., Fu, Y., Yang, K., Brahman, F., Huang, S., Bhagavatula, C., Ammanabrolu, P., Choi, Y., & Ren, X. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1034 · Cited by 50
MobileFlow: A Multimodal LLM For Mobile GUI AgentPreprint
Nong, S., Zhu, J., Wu, R. M., Jin, J., Shan, S., Huang, X., & Xu, W. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.04346 · Cited by 46
A Survey of Multi-AI Agent Collaboration: Theories, Technologies and Applications
Zhang, X., Dong, X., Wang, Y., Zhang, D., & Cao, F. (2025) · Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence (DEAI) · doi:10.1145/3745238.3745531 · Cited by 45
Self-citationPerturbation-Restrained Sequential Model EditingPreprint
Ma, J.-Y., Wang, H., Xu, H.-X., Ling, Z.-H., & Gu, J.-C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.16821 · Cited by 45
RATT: Recurrent Attention to Transient Tasks for Continual Image CaptioningPreprint
Chiaro, R. D., Twardowski, B., Bagdanov, A. D., & van de Weijer, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.06271 · Cited by 44
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
Li, Y., Wen, H., Wang, W., Li, X., Yuan, Y., Liu, G., Liu, J., Xu, W., Wang, X., Sun, Y., et al. (2024) · arXiv · doi:10.48550/arxiv.2401.05459 · Cited by 43
VideoWebArena: Evaluating Long Context Multimodal Agents with Video Understanding Web TasksPreprint
Jang, L., Li, Y., Zhao, D., Ding, C., Lin, J., Liang, P. P., Bonatti, R., & Koishida, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.19100 · Cited by 42
Fast and Continual Knowledge Graph Embedding via Incremental LoRA
Liu, J., Ke, W., Wang, P., Wang, J., Gao, J., Shang, Z., Li, G., Xu, Z., Ji, K., & Li, Y. (2024) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2024/243 · Cited by 42
Generative Negative Text Replay for Continual Vision-Language Pretraining
Yan, S., Hong, L., Xu, H., Han, J., Tuytelaars, T., Li, Z., & He, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20059-5_2 · Cited by 40
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
Chen, W., Su, Y., Zuo, J., Yang, C., Yuan, C., Chan, C.-M., Yu, H., Lu, Y., Hung, Y.-H., Qian, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.10848 · Cited by 39
JARVIS -1: Open-World Multi-Task Agents With Memory-Augmented Multimodal Language Models
Wang, Z., Cai, S., Liu, A., Jin, Y., Hou, J., Zhang, B., Lin, H., He, Z., Zheng, Z., Yang, Y., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3511593 · Cited by 36 · cited 5×
“For example, JARVIS-1 [49] improves its understanding of the environment through self-reflection and self-explanation, incorporating previous plans into its prompts.”
InfluentialAging with grace: Lifelong model editing with discrete key-value adaptors
Hartvigsen, T., Sankaranarayanan, S., Palangi, H., Kim, Y., & Ghassemi, M. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2079 · Cited by 35
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
Hao, S., Liu, T., Wang, Z., & Hu, Z. (2023) · arXiv · doi:10.48550/arxiv.2305.11554 · Cited by 35
IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation
Han, S., Chen, L., Lin, L.-M., Xu, Z., & Yu, K. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.88 · Cited by 34
Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
Huang, Z., Gutierrez, S., Kamana, H., & Macneil, S. (2023) · Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586182.3615796 · Cited by 34 · cited 1×
“When encountering a new task, the LLM agents first retrieve the most relevant experiences and add them to the working memory, then use these experiences to inform their reasoning process.”
Mamond, A. W., Kundroo, M., Yoo, S.-E., Kim, S., & Kim, T. (2025) · Sensors · doi:10.3390/s25030911 · Cited by 33 · cited 1×
“Recent studies demonstrate how federated reinforcement learning enables collaborative knowledge sharing among different agents to solve complex, dynamic problems like traf-fic optimization and task offloading [183], [184].”
Zhu, X., Chen, Y., Tian, H., Tao, C., Su, W., Yang, C., Huang, G., Li, B., Lu, L., Wang, X., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.17144 · Cited by 33
Plug-and-Play Adaptation for Continuously-updated QA
Lee, K., Han, W., Hwang, S.-W., Lee, H., Park, J., & Lee, S.-W. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.37 · Cited by 31
WebArena: A Realistic Web Environment for Building Autonomous Agents
Zhou, S., Xu, F. F., Zhu, H., Zhou, X., Lo, R., Sridhar, A., Cheng, X., Ou, T., Bisk, Y., Fried, D., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.13854 · Cited by 31
SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)
Sun, R., Arik, S. Ö., Muzio, A., Miculicich, L., Gundabathula, S., Yin, P., Dai, H., Nakhost, H., Sinha, R., Wang, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2306.00739 · Cited by 31
KTO: Model Alignment as Prospect Theoretic Optimization
Ethayarajh, K., Xu, W., Muennighoff, N., Jurafsky, D., & Kiela, D. (2024) · arXiv · doi:10.48550/arxiv.2402.01306 · Cited by 29
ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline
Xu, Y., Liu, X., Liu, X., Hou, Z., Li, Y., Zhang, X., Wang, Z., Zeng, A., Du, Z., Wenyi, Z., et al. (2024) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2024.findings-emnlp.569 · Cited by 28
Ogundare, O., Madasu, S., & Wiggins, N. (2023) · International Conference on Control, Mechatronics and Automation (ICCMA) · doi:10.1109/iccma59762.2023.10374622 · Cited by 27 · cited 1×
“Industrial applications, including robotics, modular manufacturing, and energy systems, further showcase how lifelong adaptation sustains efficiency and resilience in large-scale, high-stakes operations [177], [178].”
ScreenSpot-Pro: GUI Grounding for Professional High-Resolution Computer Use
Li, K., Meng, Z., Lin, H., Luo, Z., Tian, Y., Ma, J., Huang, Z., & Chua, T.-S. (2025) · Proceedings of the 33rd ACM International Conference on Multimedia · doi:10.1145/3746027.3755688 · Cited by 27 · cited 3×
“More advanced methods [43], [44], [45], [46], [47], [48] combine OCR with coordinate grounding, enabling agents to localize and interact with specific icons or regions on the screen.”
SpiritSight Agent: Advanced GUI Agent with One Look
Huang, Z., Cheng, Z., Pan, J., Hou, Z., & Zhan, M. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02746 · Cited by 26 · cited 1×
“In addition, some approaches adopt iterative grounding strategies [48] or image partitioning [149] to address the high-resolution demands of the GUI environment.”
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge TransferPreprint
Tang, Z., Cho, J., Tan, H. X., & Bansal, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.02681 · Cited by 23
Cai, Y., Thomason, J., & Rostami, M. G. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.466 · Cited by 22
Pan, X.-C., Chen, Y.-X., Chen, Y.-S., Sun, Y., Chen, D.-Y., Zhang, W.-H., Xie, Y.-X., Huang, Y., Zhang, Y., Gao, D.-W., et al. (2025) · arXiv.org · doi:10.48550/arxiv.2505.17826 · Cited by 22
LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
Yu, J., Xiong, H., Zhang, L., Diao, H., Zhuge, Y., Hong, L., Wang, D., Yu, J., He, Y., & Chen, L. (2024) · neural information processing systems · doi:10.52202/079017-1578 · Cited by 19
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Wang, P., Li, Z., Zhang, N., Xu, Z., Yao, Y., Jiang, Y., Xie, P., Huang, F., & Chen, H. (2024) · arXiv · doi:10.48550/arxiv.2405.14768 · Cited by 19
Towards Robust Graph Incremental Learning on Evolving Graphs
Su, J., Zou, D., Zhang, Z., & Wu, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.12987 · Cited by 19
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
Yin, D., Brahman, F., Ravichander, A., Chandu, K., Chang, K.-W., Choi, Y., & Lin, B. Y. (2024) · Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2024.acl-long.670 · Cited by 17 · cited 1×
“The capabilities that the model significantly enhances through this fine-tuning fall into two main categories: specific capabilities [122], [123], [124], [125] and general capabilities [126], [127], [128].”
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
Gur, I., Furuta, H., Huang, A., Safdari, M., Matsuo, Y., Eck, D., & Faust, A. (2023) · arXiv · doi:10.48550/arxiv.2307.12856 · Cited by 17
Entity-Agnostic Representation Learning for Parameter-Efficient Knowledge Graph Embedding
Chen, M., Zhang, W., Yao, Z., Zhu, Y., Gao, Y., Pan, J. Z., & Chen, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i4.25535 · Cited by 15
From Persona to Personalization: A Survey on Role-Playing Language Agents
Chen, J., Wang, X., Xu, R., Yuan, S., Zhang, Y., Shi, W., Xie, J., Li, S., Yang, R., Zhu, T., et al. (2024) · arXiv · doi:10.48550/arxiv.2404.18231 · Cited by 15
DelTA: An Online Document-Level Translation Agent Based on Multi-Level MemoryPreprint
Wang, Y., Zeng, J., Liu, X., Wong, D. F., Meng, F., Zhou, J., & Zhang, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.08143 · Cited by 15
Dong, Y., Zhu, X., Pan, Z., Zhu, L., & Yang, Y. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.964 · Cited by 13
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Hu, C., Fu, J., Du, C., Luo, S., Zhao, J., & Zhao, H. (2023) · arXiv · doi:10.48550/arxiv.2306.03901 · Cited by 13
MediaGPT : A Large Language Model For Chinese MediaPreprint
Wang, Z., Lu, Z., Jin, B., & Deng, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.10930 · Cited by 13
Blind Judgement: Agent-Based Supreme Court Modelling With GPT
Hamilton, S. (2023) · arXiv · doi:10.48550/arxiv.2301.05327 · Cited by 13
From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces
Shaw, P., Joshi, M., Cohan, J., Berant, J., Pasupat, P., Hu, H., Khandelwal, U., Lee, K., & Toutanova, K. N. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-1490 · Cited by 12
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
Jiang, H., Wu, Q., Luo, X., Li, D., Lin, C.-Y., Yang, Y., & Qiu, L. (2023) · arXiv · Cited by 12 · cited 1×
“We begin by outlining the key challenges lifelong LLM agents face in executing these grounding actions, then explore corresponding solutions under different environmental contexts.”
Learning Evolving Tools for Large Language ModelsPreprint
Chen, G., Zhang, Z., Cong, X., Guo, F., Wu, Y., Lin, Y., Feng, W., & Wang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.06617 · Cited by 12
Continual Egocentric Activity Recognition With Foreseeable-Generalized Visual–IMU Representations
He, C., Cheng, S., Qiu, Z., Xu, L., Meng, F., Wu, Q., & Li, H. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3371975 · Cited by 11 · cited 1×
“Generative replay [81], [82] employs an auxiliary generative model to synthesize replayed data, reducing storage demands while preserving prior knowledge.”
Multi-Agent Collaboration for Vehicular Task Offloading Using Federated Deep Reinforcement Learning
Chen, X., Xiao, B., Lin, X., Chen, Z., & Min, G. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3557898 · Cited by 10 · cited 1×
“Recent studies demonstrate how federated reinforcement learning enables collaborative knowledge sharing among different agents to solve complex, dynamic problems like traf-fic optimization and task offloading [183], [184].”
Loss of Plasticity in Continual Deep Reinforcement Learning
Abbas, Z., Zhao, R., Modayil, J., White, A., & Machado, M. C. (2023) · arXiv · doi:10.48550/arxiv.2303.07507 · Cited by 10
Scaling Relationship on Learning Mathematical Reasoning with Large Language Models
Yuan, Z., Yuan, H., Li, C., Dong, G., Lu, K., Tan, C., Zhou, C., & Zhou, J. (2023) · arXiv · doi:10.48550/arxiv.2308.01825 · Cited by 10
Self-citationMitigating the Alignment Tax of RLHF
Lin, Y., Lin, H., Xiong, W., Diao, S., Liu, J., Zhang, J., Pan, R., Wang, H., Hu, W., Zhang, H., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.06256 · Cited by 10
GPT-4V(ision) is a Generalist Web Agent, if Grounded
Zheng, B., Gou, B., Kil, J., Sun, H., & Su, Y. (2024) · arXiv · doi:10.48550/arxiv.2401.01614 · Cited by 10
A Survey on Self-Evolution of Large Language Models
Tao, Z., Lin, T.-E., Chen, X., Li, H., Wu, Y., Li, Y., Jin, Z., Huang, F., Tao, D., & Zhou, J. (2024) · arXiv · doi:10.48550/arxiv.2404.14387 · Cited by 9
FireAct: Toward Language Agent Fine-tuning
Chen, B., Shu, C., Shareghi, E., Collier, N., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2310.05915 · Cited by 9
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
Hu, M., Mu, Y., Yu, X., Ding, M., Wu, S., Shao, W., Chen, Q., Wang, B., Qiao, Y., & Luo, P. (2023) · arXiv · doi:10.48550/arxiv.2310.08582 · Cited by 9
Physics of Language Models: Part 3.2, Knowledge Manipulation
Allen-Zhu, Z., & Li, Y. (2025) · doi:10.2139/ssrn.5250621 · Cited by 8
RET-LLM: Towards a General Read-Write Memory for Large Language Models
Modarressi, A., Imani, A., Fayyaz, M., & Schütze, H. (2023) · arXiv · doi:10.48550/arxiv.2305.14322 · Cited by 8
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
Zheng, L., Wang, R., Wang, X., & An, B. (2023) · arXiv · doi:10.48550/arxiv.2306.07863 · Cited by 7
DB-GPT: Empowering Database Interactions with Private Large Language Models
Xue, S., Jiang, C., Shi, W., Cheng, F., Chen, K., Yang, H., Zhang, Z., He, J., Zhang, H., Wei, G., et al. (2023) · arXiv · doi:10.48550/arxiv.2312.17449 · Cited by 7
Plan, Eliminate, and Track - Language Models are Good Teachers for Embodied Agents
Wu, Y., Min, S. Y., Bisk, Y., Salakhutdinov, R., Azaria, A., Li, Y., Mitchell, T., & Prabhumoye, S. (2023) · arXiv · doi:10.48550/arxiv.2305.02412 · Cited by 7 · cited 1×
“In life scenarios, they act as adaptive conversational partners by integrating role-playing [165], [166] and long-context reasoning, thereby providing more natural, emotionally resonant interactions [167], and can also support household tasks in adaptive environments [168].”
Liu, N., Chen, L., Tian, X., Zou, W., Chen, K., & Cui, M. (2024) · arXiv · doi:10.48550/arxiv.2401.02777 · Cited by 7
Federated learning for privacy-preserving AI in human–robot collaboration for smart manufacturing
Rahmati, M. (2025) · Journal of Intelligent Manufacturing and Special Equipment · doi:10.1108/jimse-03-2025-0003 · Cited by 6 · cited 1×
“Protecting privacy requires the integration of techniques such as federated learning [188], differential privacy, and encrypted memory storage within the agent’s memory modules.”
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
Sarch, G., Jang, L., Tarr, M. J., Cohen, W. W., Marino, K., & Fragkiadaki, K. (2024) · arXiv · doi:10.48550/arxiv.2406.14596 · Cited by 6
Continual Vision-Language Representation Learning with Off-Diagonal Information
Ni, Z., Wei, L., Tang, S., Zhuang, Y., & Tian, Q. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.07437 · Cited by 6
JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models
Wang, Z., Cai, S., Liu, A., Jin, Y., Hou, J., Zhang, B., Lin, H., He, Z., Zheng, Z., Yang, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2311.05997 · Cited by 6
Wang, Z. Z., Mao, J., Fried, D., & Neubig, G. (2024) · arXiv · doi:10.48550/arxiv.2409.07429 · Cited by 5
H-MEM: Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
Sun, H., Zeng, S., & Zhang, B. (2026) · Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.eacl-long.15 · Cited by 4
Cheruiyot, K., Kiprotich, N., Kungurtsev, V., Mugo, K., Mwirigi, V., & Ngesa, M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.06278 · Cited by 4
Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning
Sarfraz, F., Zonooz, B., & Arani, E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.02766 · Cited by 4
EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction
Yuan, S., Song, K., Chen, J., Tan, X., Shen, Y., Kan, R., Li, D., & Yang, D. (2024) · arXiv · doi:10.48550/arxiv.2401.06201 · Cited by 4
Math Agents: Computational Infrastructure, Mathematical Embedding, and Genomics
Swan, M., Kido, T., Roland, E., & Santos, R. P. D. (2023) · arXiv · doi:10.48550/arxiv.2307.02502 · Cited by 4 · cited 1×
“In education [171], [172] and healthcare [173], agents adaptively integrate new knowledge to provide personalized teaching and decision support in safety-critical contexts.”
COPR: Continual Human Preference Learning via Optimal Policy Regularization
Zhang, H., Gui, L., Yu, L., et al. (2025) · doi:10.18653/v1/2025.findings-acl.281 · Cited by 3
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
Gou, B., Wang, R., Zheng, B., Xie, Y., Chang, C., Shu, Y., Sun, H., & Su, Y. (2024) · arXiv · doi:10.48550/arxiv.2410.05243 · Cited by 3
Enhance Lifelong Model Editing with Continuous Data-Adapter Association
Li, J., Wang, Q., Wang, Z., Zhang, Y.-D., & Mao, Z.-D. (2024) · arXiv.org · doi:10.48550/arxiv.2408.11869 · Cited by 2
LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
Zhao, J., Zu, C., Xu, H., Lu, Y., He, W., Ding, Y., Gui, T., Zhang, Q., & Huang, X. (2024) · arXiv · doi:10.48550/arxiv.2402.11550 · Cited by 2
Tree Search for Language Model Agents
Koh, J. Y., McAleer, S., Fried, D., & Salakhutdinov, R. (2024) · arXiv · doi:10.48550/arxiv.2407.01476 · Cited by 2
Research works printed but not linked: 5
- Zhou, 2024, WebArena: A realistic web environment for building autonomous agents
- Ding, 2020, CogLTX: Applying bert to long texts, 33, 12792
- Lu, 2021, Container: Context aggregation network, 34, 1960
- Zhang, 2024, CPPO: Continual learning for reinforcement learning with human feedback
- Raman, 2022, Planning with large language models via corrective re-prompting
Cited by
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052 · Cited by 70
From System 1 to System 2: A Survey of Reasoning Large Language Models
Zhang, D., Li, Z., Zhang, M.-L., Zhang, J., Liu, Z., Yao, Y., Xu, H., Zheng, J., Chen, X., Zhang, Y., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3637037 · Cited by 611
“However, standard LLMs are prone to catastrophic forgetting, where updates for new tasks overwrite previous capabilities, and often struggle with domain shifts in reasoning contexts [244].”
Self-citationDeep Reinforcement Learning in the Era of Foundation Models: A Survey
Mienye, I. D., Esenogho, E., & Modisane, C. (2026) · Computers · doi:10.3390/computers15010040 · Cited by 13
A Holistic Review of Agentic AI Frameworks, Applications, and Research Trajectories
Peykani, P., Ghanidel, S., Javadi-Sisi, I., Snåšel, V., & Mirjalili, S. (2026) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-026-10675-8 · Cited by 6
A Review of Multi-Agent AI Systems for Biological and Clinical Data Analysis
Spieser, J., Balapour, A., Meller, J., Patra, K. C., & Shamsaei, B. (2026) · Methods and Protocols · doi:10.3390/mps9020033 · Cited by 5
“Empirically, this kind of reviewer setup has been shown to reduce hallucinations in LLM-generated answers [47,48].”
Influential
Metadata
- Authors
- Zheng, J., Shi, C., Cai, X., Li, Q., Zhang, D., Li, C., Yu, D., & Ma, Q.
- Affiliations
- South China University of Technology (CN)
- Mohamed bin Zayed University of Artificial Intelligence (AE)
- Tencent (China) (CN)
- Tencent AI Lab, Bellevue, WA, USA
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2026-05
- Volume
- 48
- Issue
- 5
- Pages
- 5552-5571
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W7118167202
- Cited by
- 7
- References
- 98
- Citations by year
- 2026: 5
- FWCI
- 4.77
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Funders
- National Natural Science Foundation of China (62272173, 62273109)
- Natural Science Foundation of Guangdong Province (2024A1515010089, 2022A1515010179)
- Science and Technology Planning Project of Guangdong Province (2023A0505050106)
- National Key R&D Program of China (2023YFA1011601)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
- Keywords
- lifelong learning, continual learning, LLM agents, artificial general intelligence, catastrophic forgetting, memory modules, multisensory perception, knowledge retrieval, long-term performance
- MeSH terms
- Large Language Models, Artificial Intelligence, Humans, Language, Learning, Natural Language Processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.