Before Bringing It Up: When and How AI Companions Should Use Memor
3.60T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2610.09470.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryResearchers interviewed 14 users to study when AI companions should surface remembered information. They developed Reconsider, a single-call procedure with five checks and four handling modes, evaluated across 80 scenarios and five LLM models. LLM judges preferred it overall, though the margin did not hold for GPT or Claude.
Why it mattersA concrete memory-use framework with its own caveats: judge preferences did not replicate on two major model families. Useful reference for anyone designing companion products that retain user history.
Cited by
No citations on record.
