AI & ML interests

None defined yet.

Recent Activity

JialinLi  updated a Space 11 minutes ago
mempabench/README
JialinLi  published a Space 12 minutes ago
mempabench/README
JialinLi  updated a dataset about 13 hours ago
mempabench/mempabench-traces
View all activity

Organization Card
A robot agent holds its notebook about the user, where "Orders: just do it, don't ask" is circled in red, yet it raises a sign asking "Shall I proceed?". The user, shopping on a phone, face-palms and says "Just do it!"

Can personal agents keep up with your interaction habits across contexts and over time? MemPABench tests whether an agent's memory lets it learn when each user wants it to ask, confirm, or just act.

PaperarXiv:2610.30485
Codegithub.com/mempabench/mempabench
Websitemempabench.com
The four simulated usersmempabench-personas
The paper's runsmempabench-traces

models 0

None public yet