Metraipolis › archive › dc_2bc1f99a211e

WiSI: Wireless-in-the-Loop Self-Improvement — arXiv:2611.04437

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04437
License (as archived)
CC0-1.0
Archived
2026-11-04T19:14:06.037Z
SHA-256 of the archived text
d5c5bed7c10ebe35f64d8b7c0be7d44a3ad4158e1784d8cffb6302bb5da769b4
Stable URL of this page
https://metraipolis.com/documento/dc_2bc1f99a211e

How to cite

WiSI: Wireless-in-the-Loop Self-Improvement — arXiv:2611.04437 — arXiv (en), https://arxiv.org/abs/2611.04437 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bc1f99a211e (Metraipolis archive dc_2bc1f99a211e, sha256 d5c5bed7c10ebe35f64d8b7c0be7d44a3ad4158e1784d8cffb6302bb5da769b4)
BibTeX
@misc{dc2bc1f99a211e,
  title = {WiSI: Wireless-in-the-Loop Self-Improvement — arXiv:2611.04437},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04437},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bc1f99a211e; sha256 d5c5bed7c10ebe35f64d8b7c0be7d44a3ad4158e1784d8cffb6302bb5da769b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04437. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The growing autonomy of AI agents has enabled self-improvement, where agents iteratively refine their programs through execution feedback and performance evaluation. As these agents increasingly operate in physical environments and rely on wireless connectivity, communication conditions become an integral part of their improvement process. However, existing approaches largely assume ideal communication, overlooking how wireless conditions shape both the feedback that guides program modifications and the evaluation outcomes that determine which modifications survive. This challenge is further complicated by the coupling between agent behavior and wireless connectivity, as agents influence their own communication conditions through mobility and transmission decisions. To address this problem, we propose WiSI, a wireless-in-the-loop self-improvement framework that integrates spatiotemporal wireless channels, edge-assisted perception, and Large Language Model-driven program improvement. By incorporating wireless execution into the improvement loop, WiSI reveals how wireless execution experience shapes the generation and retention of program structures, and investigates the wireless conditions needed for robust improvement. Experiments show that agents improved under ideal links achieve only 40.0% task success under congestion, compared with 77.2% when improved under realistic wireless conditions. More importantly, wireless-aware feedback and selection jointly enable agents to discover and retain communication-efficient program structures that outperform parameter tuning and remain robust even with inaccurate run-time channel observations. We further find that moderate-load or mixed-network evaluation maintains strong performance across deployment conditions, while simplified models preserving link-rate statistics achieve comparable results without detailed spatial channel information.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv eess.SY, nuovi lavori del giorno).
Categorie arXiv: Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2611.04437 — 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 2026-11-04T18:48:22.563Z dalla pagina https://arxiv.org/list/eess.SY/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).