Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents
Open accessAbstract
The recent advent of large language models (LLM) has resulted in high-performing conversational agents such as ChatGPT. These agents must remember key information from an ongoing conversation to provide responses that are contextually relevant to the user. However, these agents have limited memory and can be distracted by irrelevant parts of the conversation. While many strategies exist to manage conversational memory, users currently lack affordances for viewing and controlling what the agent remembers, resulting in a poor mental model and conversational breakdowns. In this paper, we present Memory Sandbox, an interactive system and design probe that allows users to manage the conversational memory of LLM-powered agents. By treating memories as data objects that can be viewed, manipulated, recorded, summarized, and shared across conversations, Memory Sandbox provides interaction affordances for users to manage how the agent should ‘see’ the conversation.
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?
Text-based memory offers good interpretability and implementation convenience for long-term memory in LLMs.
“Memory in textual form (Li et al., 2023; Huang et al., 2023; Zhong et al., 2024) offers good interpretability and implementation convenience for long-term memory in LLMs.”
From Evaluating the Long-Term Memory of Large Language Models (2025) · cites this paper as Huang et al., 2023
Section 2.1 describes viewable, manipulable memory objects that make an agent’s conversational memory explicit, supporting the interpretability aspect. The paper does not establish that textual form itself provides implementation convenience, nor does it specifically assess that advantage for long-term memory. (LLM, conf=0.83)
Experimental — accuracy not yet measured
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
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173 · see citing works
Lost in the Middle: How Language Models Use Long Contexts
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., & Liang, P. (2023) · arXiv · doi:10.48550/arxiv.2307.03172 · Cited by 1,599 · see citing works
Principles of mixed-initiative user interfaces
Horvitz, E. (1999) · Proceedings of the SIGCHI conference on Human factors in computing systems the CHI is the limit - CHI '99 · doi:10.1145/302979.303030 · Cited by 1,490 · see citing works
Bier, E. A., Stone, M. C., Pier, K., Buxton, W. A. S., & DeRose, T. (1993) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/166117.166126 · Cited by 1,164 · see citing works
Zhang, Y., Liao, Q. V., & Bellamy, R. K. E. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372852 · Cited by 895 · see citing works
Wu, T., Terry, M. A., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517582 · Cited by 536 · see citing works
Agency plus automation: Designing artificial intelligence into interactive systems
Heer, J. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1807184115 · Cited by 279 · see citing works
Bringing Transparency Design into Practice
Eiband, M., Schneider, H., Bilandzic, M., Fazekas-Con, J., Haug, M., & Hussmann, H. (2018) · 23rd International Conference on Intelligent User Interfaces · doi:10.1145/3172944.3172961 · Cited by 250 · see citing works
Beyond Goldfish Memory: Long-Term Open-Domain Conversation
Xu, J., Szlam, A., & Weston, J. (2022) · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2022.acl-long.356 · Cited by 188 · see citing works
PromptMaker: Prompt-based Prototyping with Large Language Models
Jiang, E., Olson, K., Toh, E., Molina, A., Donsbach, A., Terry, M., & Cai, C. J. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3503564 · Cited by 157 · cited 1× · see citing works
“Tools are beginning to emerge that focus on how users might interact with LLMs, including mapping UI affordances to an LLM [13], grounding human-AI collaboration in a shared artifact [9], providing templates to facilitate prompt generation [10], and decomposing complex prompts to facilitate debugging [19].”
BackgroundBeyond Goldfish Memory: Long-Term Open-Domain Conversation
Xu, J., Szlam, A., & Weston, J. (2021) · arXiv · doi:10.48550/arxiv.2107.07567 · Cited by 148 · cited 2× · see citing works
“This makes it difficult for users to repair conversational breakdowns that happen when there is a misalignment between how the agent manages the memory and how the user perceives the conversation.”
BackgroundXia, H., Araujo, B. D., Grossman, T., & Wigdor, D. (2016) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858075 · Cited by 113 · see citing works
An experimental study of common ground in text-based communication
McCarthy, J., Miles, V. C., & Monk, A. F. (1991) · doi:10.1145/108844.108890 · Cited by 90 · see citing works
One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
Ma, Z., Dou, Z., Zhu, Y., Zhong, H., & Wen, J.-R. (2021) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3404835.3462828 · Cited by 78 · see citing works
Bederson, B. B., Hollan, J. D., Druin, A., et al. (1996) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/237091.237116 · Cited by 69 · see citing works
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
Ross, A., Chen, N., Hang, E. Z., Glassman, E. L., & Doshi-Velez, F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445296 · Cited by 40 · see citing works
CausalMapper: Challenging designers to think in systems with Causal Maps and Large Language Model
Huang, Z., Quan, K., Chan, J., & MacNeil, S. (2023) · Creativity and Cognition · doi:10.1145/3591196.3596818 · Cited by 24 · see citing works
Self-citationPrompt Middleware: Mapping Prompts for Large Language Models to UI AffordancesPreprint
MacNeil, S., Tran, A., Kim, J., Huang, Z., Bernstein, S., & Mogil, D. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.01142 · Cited by 8 · see citing works
Self-citationKeep Me Updated! Memory Management in Long-term Conversations
Bae, S., Kwak, D., Kang, S., Lee, M. Y., Kim, S., Jeong, Y., Kim, H., Lee, S.-W., Park, W., & Sung, N. (2022) · arXiv · doi:10.48550/arxiv.2210.08750 · Cited by 5 · see citing works
Less is More: Learning to Refine Dialogue History for Personalized Dialogue GenerationPreprint
Zhong, H., Dou, Z., Zhu, Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.08128 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 6
- [2]2. Benjamin B Bederson, James D Hollan, Allison Druin, Jason Stewart, David Rogers, and David Proft. 1996. Local tools: An alternative to tool palettes. In Proceedings of the 9th annual ACM symposium on User interface software and technology. 169-170.
- [4]4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877-1901.
- [5]5. Herbert H Clark and Edward F Schaefer. 1989. Contributing to discourse. Cogni- tive science 13, 2 (1989), 259-294.
- [17]17. Heleen Rutjes, Martijn Willemsen, and Wijnand IJsselsteijn. 2019. Considerations on explainable AI and users' mental models. In CHI 2019 Workshop: Where is the Human? Bridging the Gap Between AI and HCI. Association for Computing Machinery, Inc.
- [18]18. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Schärli, and Denny Zhou. 2023. Large language models can be easily distracted by irrelevant context. In International Conference on Machine Learning. PMLR, 31210-31227.
- [22]22. Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, and Shihang Wang. 2022. Long Time No See! Open-Domain Conversation with Long-Term Persona Memory. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, 2639-2650. https://doi.org/10.18653/v1/2022.fndings-acl.207 · DOI
Cited by
Sorted by citations
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 · see citing works
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. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4222-0 · Cited by 970 · see citing works
A survey on LLM-based multi-agent systems: Workflow, infrastructure, and challenges
Li, X., Wang, S., Zeng, S., Wu, Y., & Yang, Y. (2024) · Vicinagearth · doi:10.1007/s44336-024-00009-2 · Cited by 404 · see citing works
“In [145], it involves translating sentences into triplet configurations, while others perceive memory as a unique data object, facilitating diverse interactions [144].”
A Survey on the Memory Mechanism of Large Language Model-based Agents
Zhang, Z., Dai, Q., Bo, X., Ma, C., Li, R., Chen, X., Zhu, J., Dong, Z., & Wen, J.-R. (2025) · ACM Transactions on Information Systems · doi:10.1145/3748302 · Cited by 118 · see citing works
Memolet: Reifying the Reuse of User-AI Conversational Memories
Yen, R., & Zhao, J. (2024) · Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3654777.3676388 · Cited by 22 · see citing works
Enhancing memory retrieval in generative agents through LLM-trained cross attention networks
Hong, C., & He, Q. (2025) · Frontiers in Psychology · doi:10.3389/fpsyg.2025.1591618 · Cited by 7 · see citing works
Understanding Users' Privacy Perceptions Towards LLM's RAG-based Memory
Zhang, S., Ma, R., Ma, Y., Li, S., Xu, Y., Yi, X., & Li, H. (2025) · Proceedings of the 2025 Workshop on Human-Centered AI Privacy and Security · doi:10.1145/3733816.3760750 · Cited by 6 · see citing works
Evaluating the Long-Term Memory of Large Language Models
Jia, Z., Liu, Q., Li, H., Chen, Y., & Liu, J. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.1014 · Cited by 5 · see citing works
“Memory in textual form (Li et al., 2023; Huang et al., 2023; Zhong et al., 2024) offers good interpretability and implementation convenience for long-term memory in LLMs.”
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
Liu, J., Kong, Z., Yang, C., Yang, F., Li, T., Dong, P., Nanjekye, J., Tang, H., Yuan, G., Niu, W., et al. (2025) · arXiv · doi:10.48550/arxiv.2508.04903
“MM (Hatalis et al. 2023) suggests the use of metadata in procedural and semantic memory and the integration of external knowledge et al. 2023) present Memory Sandbox, an interactive system and design probe that allows users to manage the conversational memory of LLM-powered agents.”
- Authors
- Huang, Z., Gutierrez, S., Kamana, H., & Macneil, S.
- Affiliations
- University of California San Diego (US)
- Temple University (US)
- Venue
- Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology
- Publisher
- ACM
- Published
- 2023-10-29
- Pages
- 1-3
- OpenAlex
- W4387993371
- Semantic Scholar
- 048e0a6fa601f6f87865a054f1dca95b2e28e51d
- Cited by
- 34
- References
- 20
- Citations by year
- 2026: 8 · 2025: 18 · 2024: 8
- FWCI
- 6.04
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Symposium on User Interface Software and Technology (UIST) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Keywords
- conversational memory, memory management, large language models, chatbots, memory visualization, design probes, mental models
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
