Metraipolis › archive › dc_be7cf6821ebf

HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory — arXiv:2608.22310

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22310
License (as archived)
CC0-1.0
Archived
2026-10-18T07:41:23.311Z
SHA-256 of the archived text
6752a35c880e9d385cd000b49565a37a2bef76ff22e08b913d5bfcfcf3d76ee3
Stable URL of this page
https://metraipolis.com/documento/dc_be7cf6821ebf

How to cite

HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory — arXiv:2608.22310 — arXiv (en), https://arxiv.org/abs/2608.22310 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_be7cf6821ebf (Metraipolis archive dc_be7cf6821ebf, sha256 6752a35c880e9d385cd000b49565a37a2bef76ff22e08b913d5bfcfcf3d76ee3)
BibTeX
@misc{dcbe7cf6821ebf,
  title = {HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent Memory — arXiv:2608.22310},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22310},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_be7cf6821ebf; sha256 6752a35c880e9d385cd000b49565a37a2bef76ff22e08b913d5bfcfcf3d76ee3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22310. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-term memory is crucial for personalized responses and long-horizon agent interactions. Existing methods often rely on LLMs to compress or rewrite dialogue histories and use the transformed memories as retrieval evidence. Despite the progress in organizing fragmented contexts, two major drawbacks persist: (1) information loss from compression, which discards fine-grained but later useful details, and (2) semantic drift from rewriting, which erodes the original tone and situated context. In this work, we propose a novel Human-profile Enhanced Retrieval Optimization framework for long-term agent memory (HERO). Specifically, HERO converts the dialogue history into a traceable heterogeneous memory graph that preserves raw dialogue text as evidence for reasoning, thereby mitigating information loss. For retrieval, HERO extracts initial anchors from the current query and incorporates human profiles via an iterative graph traversal; these anchors and profiles provide guidance signals that adaptively activate the most informative regions of the graph. Experiments on two benchmark datasets show that HERO outperforms strong baselines on both factual and personalized reasoning, while providing more faithful access to raw dialogue evidence.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.22310 — 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 2026-10-18T07:37:52.714Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).