The DOI matches its Crossref record.
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Open accessAbstract
Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses, yet their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues. We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations. Building on this foundation, we further propose an enhanced variant that leverages graph-based memory representations to capture complex relational structures among conversational elements. Through comprehensive evaluations on the LOCOMO benchmark, we systematically compare our approaches against six baseline categories. Empirical results demonstrate that our methods consistently outperform all existing memory systems across four question categories: single-hop, temporal, multi-hop, and open-domain. Notably, Mem0 achieves 26% relative improvements in the LLM-as-a-Judge metric over OpenAI, while Mem0 with graph memory achieves around 2% higher overall score than the base Mem0 configuration. Beyond accuracy gains, we also markedly reduce computational overhead compared to the full-context approach. In particular, Mem0 attains a 91% lower p95 latency and saves more than 90% token cost, thereby offering a compelling balance between advanced reasoning capabilities and practical deployment constraints. Our findings highlight the critical role of structured, persistent memory mechanisms for long-term conversational coherence, paving the way for more reliable and efficient LLM-driven AI agents. Code: https://mem0.ai/research.
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
“Mem0 extracts, consolidates, and retrieves salient conversational information, including graph-based variants for relational memory [5].”
From Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents (2026) · cites this paper as [5]
In the citing paper
“At the same time, implementations remain fragmented across virtual-context managers, reflection buffers, memory-specific services, vector stores, graph layers, and framework abstractions [19, 23, 5, 21, 26, 11, 10].”
From Oracle Agent Memory as an Enterprise Memory Substrate for Long-Horizon AI Agents (2026) · cites this paper as [5]
In the citing paper
“Since many memoryenabled assistants retrieve memories using semantic similarity [Chhikara et al., 2025], the attacker can rewrite the adversarial memory goal to increase its similarity to likely future queries.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
In the citing paper
“In external summarization systems, such as Mem0 [Chhikara et al., 2025], a separate process consolidates memories asynchronously, meaning defenses cannot be applied on-the-fly.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
In the citing paper
“Our external manager adopts Mem0's open-source additive extraction prompt as a representative configuration; the evaluation does not depend on the Mem0 SDK or any specific product.”
From Hidden in Memory: Sleeper Memory Poisoning in LLM Agents (2026) · cites this paper as Chhikara et al., 2025
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cited by
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
A Survey of Personalization: From RAG to Agent
Li, X., Jia, P., Xu, D., Wen, Y., Zhang, Y., Zhang, W., Wang, W., Wang, Y., Du, Z., Li, X., et al. (2026) · ACM Transactions on Information Systems · doi:10.1145/3802586 · Cited by 63
ExpeRepair: Dual-Memory Enhanced LLM-Based Repository-Level Program Repair
Mu, F., Wang, J., Shi, L., Wang, S., LI, S.-L., & Wang, Q. (2026) · Proceedings of the ACM on software engineering. · doi:10.1145/3808181 · Cited by 49
Evaluating Long-Horizon Memory for Multi-Party Collaborative Dialogues
Hu, C., Li, T., Gao, X., Chen, H., Bai, Y., Xu, D., Lin, T., Li, X., Han, Y., Pei, J., et al. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3817589 · Cited by 45
Agentic AI in Radiology: Evolution from Large Language Models to Future Clinical Integration
Khosravi, B., Rouzrokh, P., D’Antonoli, T. A., Moassefi, M., Faghani, S., Mansuri, A., Bressem, K. K., Tejani, A. S., & Gichoya, J. W. (2026) · Radiology Artificial Intelligence · doi:10.1148/ryai.250651 · Cited by 38
Metadata
- Authors
- Chhikara, P., Khant, D., Aryan, S., Singh, T., & Yadav, D.
- Affiliations
- Mem0.ai, research@mem0.ai
- Venue
- Frontiers in Artificial Intelligence and Applications
- Publisher
- IOS Press
- Published
- 2025-10-21
- ISSN
- 0922-6389 (ISSN-L)
- 1879-8314
- OpenAlex
- W4415428439
- Cited by
- 69
- References
- 0
- Citations by year
- 2026: 62 · 2025: 7
- FWCI
- 138.55
- Type
- book chapter
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Frontiers in artificial intelligence and applications (publishedVersion, cc-by-nc)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- long-term memory, conversational AI agents, large language models, memory-centric architecture, LLM-as-a-judge, computational efficiency, persistent memory
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory. https://app.cochat.ai/papers/10.3233/faia251160
- The paper
- Chhikara, P., Khant, D., Aryan, S., Singh, T., & Yadav, D. (2025). Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory. Frontiers in Artificial Intelligence and Applications. https://doi.org/10.3233/faia251160
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.