Metraipolis › archive › dc_69b74ada98f0

Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning — arXiv:2608.10438

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10438
License (as archived)
CC0-1.0
Archived
2026-10-19T06:08:22.916Z
SHA-256 of the archived text
4563cd7c7981cba4b27228db8e831035d74b2cc223562f73cced2e7a01d1d5e2
Stable URL of this page
https://metraipolis.com/documento/dc_69b74ada98f0

How to cite

Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning — arXiv:2608.10438 — arXiv (en), https://arxiv.org/abs/2608.10438 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69b74ada98f0 (Metraipolis archive dc_69b74ada98f0, sha256 4563cd7c7981cba4b27228db8e831035d74b2cc223562f73cced2e7a01d1d5e2)
BibTeX
@misc{dc69b74ada98f0,
  title = {Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning — arXiv:2608.10438},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10438},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69b74ada98f0; sha256 4563cd7c7981cba4b27228db8e831035d74b2cc223562f73cced2e7a01d1d5e2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10438. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. For autoregressive models, tool use naturally fits the generation process: the model emits a tool call, waits for the result, and then continues generating. Diffusion language models (dLLMs), however, reason by repeatedly refining many parts of their output in parallel, making this stop-and-resume interaction pattern unnecessarily restrictive. It can force tool decisions before the model's reasoning has stabilized, delay useful observations until a discrete call finishes, and introduce redundant refinement and tool execution, potentially hurting both task accuracy and inference efficiency. We introduce Continuous Interaction Diffusion (CID), a diffusion-native model--runtime architecture that integrates tool interaction into iterative denoising. CID separates a model-read-only fact channel, a thought channel represented by a Typed Cognitive Tensor, and a display channel. Information needs can emerge before a textual or JSON call is fully serialized, allowing perceptual bindings to launch external reads while denoising continues. Returned results are projected into the evolving thought state and can revise earlier cognition and display regions. Persistent bindings reuse static results without repeated external execution and refresh changing sources when needed. CID is designed to expose evidence earlier, overlap tool latency with model computation, reduce duplicate external work, and preserve useful computation after new evidence arrives. We formalize the architecture, runtime, and training objectives, and define an evaluation protocol for task quality and end-to-end efficiency. This first paper focuses on read-only tools and makes no empirical performance claims.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.10438 — 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 2026-10-19T05:57:28.267Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).