A memory-augmented agent must decide which memories to keep, merge and retrieve, and its only evidence of their value is its retrieval log: the memories it retrieved in each episode and whether it succeeded. Existing methods assign every memory a value from this log, even when the log cannot separate one memory's contr...
RealCompanion, ten real relationships between people and an AI companion, with 27,218 messages over up to 120 days, shows that understanding a person depends on knowing when their past matters and where what they shared ends, and only real conversations can test it.
Arman Behnam, Sunglyoung Kim, Jia-Yi Yu et al.· 0 citations
CERTID uses the sound and complete causal identification algorithm ID to certify whether an effect is identifiable from a given graph and query, and verifies returned formulas against structural causal models whose interventional distributions are known exactly.
SaCRL is introduced, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge, and provides theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-dist...
Memory-augmented large language models must decide which memories to retain, and recent systems do so by estimating each memory's effect on task performance. However, these estimates rely entirely on retrieved memories. When a memory is never retrieved, store-level interventions produce identical outcomes, leaving its...
A companion that talks with a person for months should come to understand them. It should remember what they said, infer who they are, and know when the past bears on the message in front of it. Testing this requires a real person's record, and such records are private, so benchmarks generate the person and the questio...
Arman Behnam, Sunglyoung Kim, Liang-Wei Yang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.