KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory
This paper introduces KITE, a vector-free framework for memory retrieval in LLM agents that formulates memory retrieval as an explicit decision procedure.
KITE is novel in its use of a governed topic vocabulary to unify memory construction and query compilation.
Before reading this…
Applications
- →Conversational AI
- →Language models
To understand this paper, make sure you know these concepts first:
- Knowledge of language models and memory retrievalfind papers →
- Understanding of conversational AIfind papers →
Abstract
More Like ThisMany long-term memory systems for LLM agents are built around embedding-based retrieval. Al- though effective for semantic matching, similarity ranking alone does not establish whether re- trieved memories satisfy the conditions implied by a question. In this paper, we introduce KITE (Knowledge-Indexed Temporal Evidence), a vector-free framework that formulates memory re- trieval as an explicit decision procedure. KITE organizes multi-session conversations as structured knowledge indexed by a governed topic vocabulary, which evolves through controlled expansion and consolidation. At query time, questions are compiled into inspectable retrieval plans over the same knowledge index that guides memory construction. The plans are then executed through fixed lookup and ranking operations, while sparse lexical retrieval recovers surface details omitted from the structured representation. Experiments on LoCoMo and LongMemEval-S show that KITE achieves 93.5% and 86.0% accuracy while using only about 1.6k reader-context tokens per ques- tion. These results demonstrate that conversational memory can move beyond similarity ranking by unifying memory construction and query compilation around a governed index, turning retrieval into an inspectable decision procedure for determining which evidence satisfies the question.