Metraipolis › archive › dc_86df710f18e3

ECHO: A Cognitively Inspired, Auditable Memory Plane for Long-Horizon Agents — arXiv:2608.21755

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21755
License (as archived)
CC0-1.0
Archived
2026-10-18T07:38:49.738Z
SHA-256 of the archived text
dd0d45bf1c57d438696dc06aec48d9b1add0a18ca0d115bf70c0b184fc53973f
Stable URL of this page
https://metraipolis.com/documento/dc_86df710f18e3

How to cite

ECHO: A Cognitively Inspired, Auditable Memory Plane for Long-Horizon Agents — arXiv:2608.21755 — arXiv (en), https://arxiv.org/abs/2608.21755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_86df710f18e3 (Metraipolis archive dc_86df710f18e3, sha256 dd0d45bf1c57d438696dc06aec48d9b1add0a18ca0d115bf70c0b184fc53973f)
BibTeX
@misc{dc86df710f18e3,
  title = {ECHO: A Cognitively Inspired, Auditable Memory Plane for Long-Horizon Agents — arXiv:2608.21755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_86df710f18e3; sha256 dd0d45bf1c57d438696dc06aec48d9b1add0a18ca0d115bf70c0b184fc53973f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-horizon agents need memory that identifies relevant experience, resolves revisions, and exposes checkable provenance. We present ECHO (Embodied Context and History Orchestration), an auditable memory architecture and service prototype inspired by episodic encoding, consolidation, contextual reinstatement, reconsolidation, and executive control. This is functional inspiration, not neural equivalence; the empirical analysis focuses on retrieval and context construction. Development runs reach 96.29% Hit@10 and 73.64% turn Recall@5 on 1,536 LoCoMo category 1-4 questions, and 97.60% Hit@10, 88.84% turn Recall@5, and 88.71% session Recall@5 on all 500 LongMemEval-S questions. A five-history BEAM gate fails, and in a separate matched 91-question QA sample Mem0 OSS scores 64.84% versus ECHO's 41.76% (exact McNemar p = 0.00107), with a history-cluster interval crossing zero. A post-hoc audit found source-specific phrases in the query-expansion rules. Although no gold answer field entered the runtime, expansion-enabled retrieval scores are therefore descriptive development measurements, not independent confirmation.

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/2608.21755 — 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 2026-10-18T07:37:52.666Z 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).