Metraipolis › archive › dc_cbafb13ce258

GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory — arXiv:2608.26983

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26983
License (as archived)
CC0-1.0
Archived
2026-10-17T14:23:17.398Z
SHA-256 of the archived text
716770ed4fbd6407524b759670a42cbd7a633054c96ff3090a4aaea96e386e58
Stable URL of this page
https://metraipolis.com/documento/dc_cbafb13ce258

How to cite

GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory — arXiv:2608.26983 — arXiv (en), https://arxiv.org/abs/2608.26983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbafb13ce258 (Metraipolis archive dc_cbafb13ce258, sha256 716770ed4fbd6407524b759670a42cbd7a633054c96ff3090a4aaea96e386e58)
BibTeX
@misc{dccbafb13ce258,
  title = {GraphMemix: Query-Aware Evidence Forests for Long-Term Multimodal Agent Memory — arXiv:2608.26983},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26983},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbafb13ce258; sha256 716770ed4fbd6407524b759670a42cbd7a633054c96ff3090a4aaea96e386e58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Organizing long-term memory for multimodal agents remains challenging because existing methods either suffer from expensive question-agnostic offline summaries or naive embedding similarity matching that introduces incomplete and redundant context. To address these issues, we propose GraphMemix, a combinatorial-optimization graph memory framework that models memory organization as query-aware evidence-forest construction. Specifically, our method consists of three key components:(1) candidate graph construction, which expands multi-view seed memories through schema and semantic relations to acquire query-aware original context; (2) evidence utility and activation costs, which decouples direct memory support from anchor-conditioned relation verification to suppress redundant or conflicting information; and (3) forest optimization, which jointly selects a forest-format memory context under a maximum evidence budget and its reliable relational structure. By organizing memory into a query-relevant subgraph, the method avoids substantial lifecycle cost and recovers low-similarity complementary evidence. Experimental results across four long-term multimodal memory benchmarks demonstrate significant improvements with different foundation models and establish a new Pareto frontier between accuracy and lifecycle cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.26983 — 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 2026-10-17T13:16:53.536Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).