Metraipolis › archive › dc_6239ddacc258

Revision-Aware Independent Agent Graphs for Dynamic Reasoning — arXiv:2610.01249

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01249
License (as archived)
CC0-1.0
Archived
2026-10-06T12:04:19.972Z
SHA-256 of the archived text
3e29f6df971dc8d8d15921c69f7df416da0af63968dedb456fcf768c47c2d99f
Stable URL of this page
https://metraipolis.com/documento/dc_6239ddacc258

How to cite

Revision-Aware Independent Agent Graphs for Dynamic Reasoning — arXiv:2610.01249 — arXiv (en), https://arxiv.org/abs/2610.01249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6239ddacc258 (Metraipolis archive dc_6239ddacc258, sha256 3e29f6df971dc8d8d15921c69f7df416da0af63968dedb456fcf768c47c2d99f)
BibTeX
@misc{dc6239ddacc258,
  title = {Revision-Aware Independent Agent Graphs for Dynamic Reasoning — arXiv:2610.01249},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01249},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6239ddacc258; sha256 3e29f6df971dc8d8d15921c69f7df416da0af63968dedb456fcf768c47c2d99f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task binding. We therefore study \emph{dynamic task routing}, in which an event stream revises task bindings and a system must select the document version valid at each query time before solving it. To study this problem, we repurpose six widely used benchmarks: MMLU, MMLU-Pro, MedMCQA, MATH, GPQA, and HumanEval into 31{,}119 dynamic episodes comprising 373{,}428 temporally categorized queries. This setting exposes a central trade-off: recomputing after every event wastes work, whereas unguarded reuse returns stale conclusions. We introduce the Revision-Aware Independent Agent Graph (RIAG), a bounded multi-agent policy that separates deterministic temporal resolution from task reasoning. RIAG caches solutions by immutable document identity, starts each fresh task with two unexposed attempts, and conditionally invokes audit and repair, using at most four calls per document version. On this collection, homogeneous RIAG achieves 54.24\% joint routing-and-answer accuracy at 0.62 calls/query, compared with 32.22\% at 18.00 calls/query for the strongest comparison method; heterogeneous RIAG reaches 49.78\% at 0.63 calls/query.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.01249 — 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 2026-10-06T10:21:27.927Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).