Metraipolis › archive › dc_bfa5e51bc119
AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory — arXiv:2609.21940
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21940
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:05:37.885Z
- SHA-256 of the archived text
2cdf148d944de80ee2103d0ac05bf1988d684f335e612e32d15eaf56e08dfee2- Stable URL of this page
https://metraipolis.com/documento/dc_bfa5e51bc119
How to cite
AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory — arXiv:2609.21940 — arXiv (en), https://arxiv.org/abs/2609.21940 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bfa5e51bc119 (Metraipolis archive dc_bfa5e51bc119, sha256 2cdf148d944de80ee2103d0ac05bf1988d684f335e612e32d15eaf56e08dfee2)
BibTeX
@misc{dcbfa5e51bc119,
title = {AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory — arXiv:2609.21940},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21940},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bfa5e51bc119; sha256 2cdf148d944de80ee2103d0ac05bf1988d684f335e612e32d15eaf56e08dfee2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21940. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing memory systems typically rely on fixed granularities or static schemas, but these designs struggle when heterogeneous information, such as preferences, events, constraints, and temporal updates, is embedded in a single mixed representation. The resulting semantic interference makes top-K retrieval sensitive to noise and often leaves relevant evidence poorly ranked. We present AutoViewMem, a data-driven framework that organizes long-term conversational memory into self-configuring, low-overlap semantic views before indexing. AutoViewMem discovers candidate views from interaction traces, selects a compact complementary view set, and uses these views to guide write-time structured extraction of provenance-grounded memories. This representation-first design moves semantic disentanglement from retrieval time to write time, allowing standard top-K similarity search to retrieve focused evidence without explicit routing or iterative retrieval. We further apply offline consolidation to improve memory compactness and consistency. Experiments on the LoCoMo and PersonaMem benchmarks, under both Qwen3-8B and Qwen3-14B backbones, show that AutoViewMem improves long-horizon question answering and personalization over strong memory baselines while preserving a simple inference pipeline. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.21940 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T00:23:42.481Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).