analiza aiqbench
PersonaTree introduces a structured lifecycle memory framework that explicitly models schema formation to support persistent LLM agents, outperforming existing methods on six benchmarks across multiple backbones. By utilizing a three-level tree architecture with confidence-guided consolidation and query-conditioned retrieval, the system efficiently balances detailed evidence retention with compact context budgets. This approach offers a concrete solution for improving person understanding and alignment in long-term agent interactions without relying on unstructured memory dumps.
PersonaTree: Structured Lifecycle Memory for Person Understanding in LLM Agents
arXiv:2606.04780v1 Announce Type: new Abstract: Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing agent memory methods emphasize information retention and retrieval, yet give limited account of how accumulated interaction evidence is abstracted into person understanding. We view this process as schema formation, where situated evidence is abstracted into reusable patterns and stable person level claims. We introduce PersonaTree, a structured lifecycle memory framework that realizes this view as a three level persona tree with explicit support paths from evidence to claims. PersonaTree maintains the tree through conservative writing, confidence guided consolidation, and query conditioned path retrieval, returning only the evidence depth required by each query. Across six person understanding and persistent memory benchmarks with three answer backbones, PersonaTree ranks first in 12 of 18 compact scores and reaches the top two in 16 settings. Ablations show that hierarchy improves abstract person understanding on KnowMe, while support path retrieval improves RealPref alignment under a comparable context budget.
Citește articolul complet pe arXiv