TY - GEN
T1 - From Storage to Interpretation
T2 - 13th International Conference on Human-Agent Interaction, HAI 2025
AU - Jones, Brennan
AU - Ponochevnyi, Nazar
AU - Stemmler, Kelsey
AU - Su, Emily
AU - Kim, Young Ho
AU - Kuzminykh, Anastasia
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2026/1/2
Y1 - 2026/1/2
N2 - To provide long-term personalized assistance to users, AI agents must have effective long-term memory (LTM). However, there is little understanding of users' perceptions, practices, and challenges with LTM in agents. We interviewed 21 users of agents such as ChatGPT and Claude to understand people's everyday experiences with agent LTM. Our findings shed light on the flow of memory in agents as a three-stage process consisting of (1) information intake, (2) storage and management, and (3) retrieval and interpretation. Users' perceptions of agent LTM are mainly influenced by Stage 3, and thus users' interactions with agent LTM are mainly attempts at influencing and understanding how the agent retrieves and interprets information from memory. Therefore, we recommend that technological approaches to user interaction with agent LTM focus at least as much on memory retrieval and interpretation as they do on memory intake, storage, and management.
AB - To provide long-term personalized assistance to users, AI agents must have effective long-term memory (LTM). However, there is little understanding of users' perceptions, practices, and challenges with LTM in agents. We interviewed 21 users of agents such as ChatGPT and Claude to understand people's everyday experiences with agent LTM. Our findings shed light on the flow of memory in agents as a three-stage process consisting of (1) information intake, (2) storage and management, and (3) retrieval and interpretation. Users' perceptions of agent LTM are mainly influenced by Stage 3, and thus users' interactions with agent LTM are mainly attempts at influencing and understanding how the agent retrieves and interprets information from memory. Therefore, we recommend that technological approaches to user interaction with agent LTM focus at least as much on memory retrieval and interpretation as they do on memory intake, storage, and management.
KW - human-agent interaction
KW - human-AI interaction
KW - language models
KW - memory
KW - personalization
UR - https://www.scopus.com/pages/publications/105027425103
U2 - 10.1145/3765766.3765843
DO - 10.1145/3765766.3765843
M3 - Conference Proceeding
AN - SCOPUS:105027425103
T3 - HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction
SP - 436
EP - 438
BT - HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction
A2 - Osawa, Hirotaka
A2 - Lindgren, Helena
A2 - Steinfeld, Aaron
A2 - Foster, Mary Ellen
A2 - Okada, Shogo
A2 - Zhu, Haiyi
PB - Association for Computing Machinery, Inc
Y2 - 10 November 2025 through 13 November 2025
ER -