Metraipolis › archive › dc_f80ab841bf55

LEMCA: LLM-Guided Synthesis of Efficient Mode-Switching Control Architectures — arXiv:2609.21319

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21319
License (as archived)
CC0-1.0
Archived
2026-10-10T02:30:06.291Z
SHA-256 of the archived text
5f7c23a49babea836eacdf008ee8deedbee01ff656eb4317254ec81ff935b304
Stable URL of this page
https://metraipolis.com/documento/dc_f80ab841bf55

How to cite

LEMCA: LLM-Guided Synthesis of Efficient Mode-Switching Control Architectures — arXiv:2609.21319 — arXiv (en), https://arxiv.org/abs/2609.21319 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f80ab841bf55 (Metraipolis archive dc_f80ab841bf55, sha256 5f7c23a49babea836eacdf008ee8deedbee01ff656eb4317254ec81ff935b304)
BibTeX
@misc{dcf80ab841bf55,
  title = {LEMCA: LLM-Guided Synthesis of Efficient Mode-Switching Control Architectures — arXiv:2609.21319},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21319},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f80ab841bf55; sha256 5f7c23a49babea836eacdf008ee8deedbee01ff656eb4317254ec81ff935b304},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21319. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physical control tasks in the natural world, such as driving or object manipulation, frequently exhibit dramatic variations in sensory and compute complexity over time. Correspondingly, a natural resource-efficient choice for robot control is to dynamically switch between control modes with varying resource allocations. However, such "mode-switching controllers" (MSCs) have historically required laborious, expert-driven design and synthesis for each new task. Driven by these design difficulties, modern robotic control architectures often fall back to a wasteful "monolithic" one-size-fits-all structure, where resource allocation is permanently anchored to the hardest, most resource-intensive task phases. To facilitate the design of performant yet efficient MSCs, we propose LLM-Guided synthesis of Efficient Mode-Switching Control Architectures (LEMCA). LEMCA represents MSC designs as interpretable programs to be iteratively refined in an evolutionary loop. To evaluate design fitness, we propose MSC-compatible extensions of automated controller synthesis approaches, such as reinforcement learning in simulation. LEMCA then leverages the semantic priors, reasoning, and coding capabilities of Large Language Models (LLMs) to iteratively edit controller modes, their corresponding sensory-compute resource allocations, and mode transitions. Our experiments across diverse control benchmarks show that LEMCA consistently discovers strategies that surpass the Pareto frontier of monolithic designs by reclaiming wasted resources during "easy" task phases. LEMCA thus presents an automated, low-effort path to synthesize resource-efficient MSC designs.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.21319 — 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 2026-10-10T02:09:55.332Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).