Metraipolis › archive › dc_a4a1924ecdf4
When Do LLM Agents Help? Deadline-Aware Mixed-Criticality Task Scheduling at the Autonomous-Vehicle Edge — arXiv:2608.19557
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19557
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T11:36:38.872Z
- SHA-256 of the archived text
fdd335017b0e6fdf8a631c45fbc57865a61a2097b578b2afc0b5079ea41e9cd7- Stable URL of this page
https://metraipolis.com/documento/dc_a4a1924ecdf4
How to cite
When Do LLM Agents Help? Deadline-Aware Mixed-Criticality Task Scheduling at the Autonomous-Vehicle Edge — arXiv:2608.19557 — arXiv (en), https://arxiv.org/abs/2608.19557 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4a1924ecdf4 (Metraipolis archive dc_a4a1924ecdf4, sha256 fdd335017b0e6fdf8a631c45fbc57865a61a2097b578b2afc0b5079ea41e9cd7)
BibTeX
@misc{dca4a1924ecdf4,
title = {When Do LLM Agents Help? Deadline-Aware Mixed-Criticality Task Scheduling at the Autonomous-Vehicle Edge — arXiv:2608.19557},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19557},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4a1924ecdf4; sha256 fdd335017b0e6fdf8a631c45fbc57865a61a2097b578b2afc0b5079ea41e9cd7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19557. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous vehicles offload latency-sensitive perception tasks to nearby mobile edge computing (MEC) servers, where a missed safety-critical task is unsafe rather than merely degraded. Large language models (LLMs) are increasingly proposed as adaptive, explainable schedulers, yet evidence of when they help is scarce. We study deadline-aware, mixed-criticality scheduling on heterogeneous MEC servers, where time-critical (TC) tasks must be protected at a controlled cost to best-effort traffic, and ask whether a multi-agent LLM control layer improves on a strong heuristic. We answer in two steps. First we build the heuristic: a windowed contract-net auction that orders each admission window time-critical-first by earliest deadline and places tasks by earliest-finish-time. Across 60 instances on three topologies and 15 baselines under an identical online constraint, it attains a TC completion rate of 0.902, above every baseline (Holm-corrected p < 0.001; best baseline 0.838) and at 0.87 of a CP-SAT upper bound. Second, we add the LLM control plane. A controlled decomposition traces the scheduler's advantage to two ordinary factors, the batching horizon and time-critical-first ordering; the auction, the per-window LLM policy, and online adaptation add nothing while the load is stationary, where the heuristic is already near-optimal. Under a mid-run surge of safety-critical tasks the picture changes, and the LLM control plane gains significantly over both the static heuristic and the bandit. LLM orchestration therefore earns its cost only when non-stationarity opens headroom a fixed policy cannot use. We report control-plane latency and rationale, and release all code and seeded instances. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.MA). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.19557 — 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 2026-10-18T11:30:10.503Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).