How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
Open accessAbstract
Zidi Xiong, Yuping Lin, Wenya Xie, Pengfei He, Zirui Liu, Jiliang Tang, Himabindu Lakkaraju, Zhen Xiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Stored information affects a decision only after it enters the active context at the right time, and reusing task-misaligned experience can propagate errors.
“Stored information, however, affects a decision only after it enters the active context at the right time, and reusing task-misaligned experience can propagate errors (Xiong et al., 2026).”
From Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model Agents (2026) · cites this paper as Xiong et al., 2026
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 4
- Jiageng Mao, Junjie Ye, Yuxi Qian, Marco Pavone, and Yue Wang. 2024. A language agent for autonomous driving. In First Conference on Language Modeling.
- Andrew Nuxoll and John E. Laird. 2007. Extending cog- nitive architecture with episodic memory. In AAAI Conference on Artificial Intelligence.
- Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. 2025. Agent workflow memory. In Forty-second International Conference on Machine Learning.
- Longtao Zheng, Rundong Wang, Xinrun Wang, and Bo An. 2024. Synapse: Trajectory-as-exemplar prompting with memory for computer control. In The Twelfth International Conference on Learning Representations.
Cited by
Sorted by citations
Maragheh, R. Y., & Deldjoo, Y. (2026) · ACM Transactions on Recommender Systems · doi:10.1145/3845988 · Cited by 14 · see citing works
Yan, S., Yang, X., Huang, Z., Nie, E., Ding, Z., Li, Z., Ma, X., Bi, J., Kersting, K., Pan, J. Z., et al. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.583 · Cited by 10 · see citing works
A survey of foundation models for IoT: taxonomy and criteria-based analysis
Wei, H., Lee, D. Y., Rohal, S., Hu, Z., Rossi, R. A., Fang, S., & Pan, S. (2025) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-025-00208-w · Cited by 8 · see citing works
MemIndex: Agentic Event-based Distributed Memory Management for Multi-agent Systems
Saleh, A., Tarkoma, S., Lindgren, A., Donta, P. K., Dustdar, S., Pirttikangas, S., & Lovén, L. (2025) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3774946 · Cited by 6 · see citing works
Ying, T., Wang, L., Hu, P., & Ding, T. (2026) · International Conference on Electronic Technology and Information Science (ICETIS) · doi:10.1109/icetis70504.2026.11633437 · Cited by 5 · see citing works
Yu, Y., Yao, L., Xie, Y., Tan, Q., Feng, J., Li, Y., & Wu, L. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.981 · Cited by 4 · see citing works
Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
Oh, C., Park, S., Kim, T. E., Li, J., Li, W., Yeh, S., Du, S., Hassani, H., Bogdan, P., Song, D., et al. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.738 · Cited by 4 · see citing works
Nguyen, P., & Pham, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2014-4_26 · Cited by 2 · see citing works
Memory Management and Contextual Consistency for Long-Running Low-Code Agents
Xu, J., & Lu, Q. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-20746-3_32 · Cited by 1 · see citing works
Kasneci, G., & Kasneci, E. (2026) · AI and Ethics · doi:10.1007/s43681-026-01132-0 · Cited by 1 · see citing works
Membership Inference Attacks on In-Context Learning Recommendation
He, J., Chen, M.-C., Chen, X., Fang, X., Gu, Y., & Chen, K. (2026) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3773078.3831733 · Cited by 1 · see citing works
Peng, H., Zheng, Y., Liu, Z., & Lam, K. (2026) · doi:10.36227/techrxiv.177219979.94060974/v1 · Cited by 1 · see citing works
Self-citationLiu, Q., Wang, M., & Xie, J. (2026) · 2026 6th International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) · doi:10.1109/mlise70044.2026.11607496
Sun, X., Wang, Q., Li, H., & Chen, L. (2026) · arXiv · doi:10.48550/arxiv.2608.03137
Narrative Plasticity and State Stickiness: Designing Hybrid AI Systems for High-Stakes Communication
Kessler, D. T., Overney, C., Shen, J. J., & Roy, D. K. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3813073
Demystify the Role of Memory in Machine Learning Engineering Agents
Zhao, X., Wang, J., Chen, Y., Pan, M., Yeh, C. M., Sun, J., Zheng, Y., Das, M., & Chen, T. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.525
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human–Agent Interaction
Huang, Z., Tian, M., Wang, X., Xu, J., Guo, Z., Qian, Q., Song, K., Yuan, J., Lv, C., & Zheng, X. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.670
Temporal Poisoning: a Non-Adversarial, Timing-Induced Instability in Long-Term Memory of LLM Agents
Semu, M., Biswas, M., & Yu, W. (2026) · IEEE/ACIS International Conference on Software Engineering Research, Management and Applications (SERA) · doi:10.1109/sera69989.2026.11618645
Agentic Intelligence: Foundations, Architectures, and Applications
Patil, H. V., Rathi, D. K. G., Dengi, O., Kolhe, D. S. D., Gadekar, D. S. H., & Chandgude, D. V. S. (2026) · doi:10.70593/978-81-69589-30-7
Correcting AI-generated false criminal allegations: a human-rights framework for remedial closurePreprint
Hanane, M., Gong, X., & Liu, Y. (2026) · Research Square · doi:10.21203/rs.3.rs-11036486/v1
Shimomoto, T. (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.20379919
SkillForge: Learning from Success–Failure Boundaries for Consistent Long-Horizon Agents
Wan, G., Wang, H., Ling, X., Ling, M., Ren, X., & Li, S. (2026) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/2026.emnlp-main.1954
Agentic AI and Autonomous LLM Systems: A Scientific Literature Review
Karthick, S., & Sherill, A. (2026) · International Journal of Creative and Open Research in Engineering and Management · doi:10.55041/ijcope.v2i10.194
- Authors
- Xiong, Z., Lin, Y., Xie, W., He, P., Liu, Z., Tang, J., Lakkaraju, H., & Xiang, Z.
- Affiliations
- Harvard University (US)
- Michigan State University (US)
- University of Minnesota (US)
- University of Georgia (US)
- Venue
- Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2026
- Pages
- 623-645
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W7166848218
- Cited by
- 4
- References
- 0
- Citations by year
- 2026: 4
- FWCI
- 35.74
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- LLM agents, memory management, agent behavior
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
