Metraipolis › archive › dc_5ffca79da3c9

Do Not Restart: Residual Completion for Stateful Agent Handoffs — arXiv:2609.13800

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13800
License (as archived)
CC0-1.0
Archived
2026-10-15T22:47:22.129Z
SHA-256 of the archived text
b9a0f8a4d3f9916d5c1321c516c422e1bda15128412c65f814a26cef6f8491f6
Stable URL of this page
https://metraipolis.com/documento/dc_5ffca79da3c9

How to cite

Do Not Restart: Residual Completion for Stateful Agent Handoffs — arXiv:2609.13800 — arXiv (en), https://arxiv.org/abs/2609.13800 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ffca79da3c9 (Metraipolis archive dc_5ffca79da3c9, sha256 b9a0f8a4d3f9916d5c1321c516c422e1bda15128412c65f814a26cef6f8491f6)
BibTeX
@misc{dc5ffca79da3c9,
  title = {Do Not Restart: Residual Completion for Stateful Agent Handoffs — arXiv:2609.13800},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13800},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ffca79da3c9; sha256 b9a0f8a4d3f9916d5c1321c516c422e1bda15128412c65f814a26cef6f8491f6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13800. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Routing and cascades reduce tool-agent cost by transferring control across models, but stateful handoffs must preserve accepted choices, realized effects, and unfinished obligations. We formulate this as commitment-constrained residual completion and introduce Commitment-Frontier Residual Completion (CFRC). CFRC enforces target-before-proposal, whole-proposal-before-authority, and live-evidence-before-success: it freezes a residual contract from accepted progress, closes the successor continuation into an evidence-linked graph, and admits execution only when the remainder is covered, with live receipts discharging obligations. We establish contract-relative partial correctness, which extends to the original residual request under complete contract construction. Across five environments and two same-provider model pairs, CFRC achieves comparable macro accuracy to strong full-task agents at 22.0% to 34.6% mean per-surface cost, with additional cross-provider results demonstrating broader transfer.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13800 — 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 2026-10-15T22:29:03.143Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).