From Storage to Interpretation: User Perceptions, Practices, and Challenges with Long-term Memory in Agents
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.035 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.006 | 0.006 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".