A hierarchical compositional architecture using ASP filtering, mined attribute concepts, and user-specific workflow patterns outperforms GPT-5.1 and ablations on personalized command disambiguation in a simulated household.
Combining LLM, Non-monotonic Logical Reasoning, and Human-in-the-loop Feedback in an Assistive AI Agent
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hierarchical Compositionality for An Assistive AI Agent
A hierarchical compositional architecture using ASP filtering, mined attribute concepts, and user-specific workflow patterns outperforms GPT-5.1 and ablations on personalized command disambiguation in a simulated household.