Metraipolis › archive › dc_2bbadde814bb

ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery — arXiv:2608.28704

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.28704
License (as archived): CC0-1.0
Archived: 2026-10-17T07:43:48.695Z
SHA-256 of the archived text: e53896180a48e2cf39daaf1ecd9a11e81f113c1d5f34f4c4f4c941cd564ddf9e
Stable URL of this page: https://metraipolis.com/documento/dc_2bbadde814bb

How to cite

ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery — arXiv:2608.28704 — arXiv (en), https://arxiv.org/abs/2608.28704 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bbadde814bb (Metraipolis archive dc_2bbadde814bb, sha256 e53896180a48e2cf39daaf1ecd9a11e81f113c1d5f34f4c4f4c941cd564ddf9e)

BibTeX

@misc{dc2bbadde814bb,
  title = {ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery — arXiv:2608.28704},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28704},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bbadde814bb; sha256 e53896180a48e2cf39daaf1ecd9a11e81f113c1d5f34f4c4f4c941cd564ddf9e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28704. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate states can propagate and cause inconsistent decisions and unreliable outputs. Existing reasoning approaches mainly rely on iterative planning, self-reflection, augmented memory, or verification, but rarely localize and selectively repair faulty reasoning. We present ORDDAR (Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery), a reasoning framework that models reasoning as cognitive state transitions, detects localized distortions, retrieves related reasoning from prior experiences, and repairs only the affected states. ORDDAR therefore performs recovery at the local reasoning-transition level rather than regenerating the complete trajectory. Experiments across mathematical, commonsense, multi-hop, and clinical reasoning benchmarks demonstrate improved reasoning quality, recovery ability, and interpretability over multiple evaluated reasoning baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.28704 — 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 2026-10-17T07:28:26.475Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).