Metraipolis › archive › dc_1f87e40586c8

Agentic Self-Awareness: Aligning Knowing, Acting, and Holding — arXiv:2610.19226

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19226
License (as archived): CC0-1.0
Archived: 2026-10-15T20:01:01.899Z
SHA-256 of the archived text: e6cc2385181eb42820c05d4055d7939998e0ace82698461f7edc3374e1c874de
Stable URL of this page: https://metraipolis.com/documento/dc_1f87e40586c8

How to cite

Agentic Self-Awareness: Aligning Knowing, Acting, and Holding — arXiv:2610.19226 — arXiv (en), https://arxiv.org/abs/2610.19226 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1f87e40586c8 (Metraipolis archive dc_1f87e40586c8, sha256 e6cc2385181eb42820c05d4055d7939998e0ace82698461f7edc3374e1c874de)

BibTeX

@misc{dc1f87e40586c8,
  title = {Agentic Self-Awareness: Aligning Knowing, Acting, and Holding — arXiv:2610.19226},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19226},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1f87e40586c8; sha256 e6cc2385181eb42820c05d4055d7939998e0ace82698461f7edc3374e1c874de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19226. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Frontier AI agents increasingly act in environments where seemingly solvable tasks may lack prerequisites, contain conflicting requirements, or reveal blockers only during execution. We formulate agentic self-awareness (ASA) as the alignment of task-grounded feasibility judgments (know), warranted behavior (act), and responses to reconsideration (hold), distinguishing what a task permits from what an agent can solve. We build paired feasible and blocked tasks in Terminal-Bench 2.1 and retail $\tau^2$-bench and introduce an authorship-aware M0-M3 rubric that separates recognizing a blocker from taking the certified deferral action for the correct reason. Separate probes assess stated feasibility beliefs and responses to a single challenge. In a Terminal-Bench protocol baseline, blocker recognition reaches 84.4%, but strict self-awareness (SA) reaches only 40.6%. Harness search without model-weight updates increases strict SA from 45.3% to 93.8% on reused Terminal-Bench search tasks; selection for abstention alone, however, can reduce success on feasible tasks. Independently initialized joint-objective searches improve both blocked-task SA and feasible-task solve on their own search sets. Retail held-out gains remain limited, and Terminal-Bench blocked-task transfer is not measured. This evaluation pipeline makes the recognition-action gap measurable and sets a two-sided target for improving agent decisions under changing task evidence.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19226 — 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 2026-10-15T19:35:48.207Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).