Tag
The paper proposes a zero-inference prospective term for personal memory retrieval that boosts memory items linked to future commitments without query-time computation. It shows improved recall on a synthetic task set and positions this as part of a layered architecture for proactive AI assistants.
This paper introduces TANGLE, a benchmark for evaluating LLM agents' cognitive behavior under irreducible conflicts in personal memory, assessing dimensions like conflict perception and memory faithfulness.