2 citations · 2 across the 2 of their papers we have counts for
5 papers · 1 filter
Top- Retrieval Leaves Memory Value Undetermined
Arman Behnam
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 episod…
Reasoning Models Are Accurate but Unsound on Identification
Arman Behnam, Binghui Wang
A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers a nonidentifiable one. The…
Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval
Arman Behnam, Binghui Wang
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 estimat…
RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations
Arman Behnam, Sunglyoung Kim, Liangwei Yang +2
An AI companion that talks with someone for months should come to understand them. It should know who they are, remember what they said, and recognize when something from the past…
Structure-agnostic Causal Representation Learning
Arman Behnam, Binghui Wang
Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal struct…