Metraipolis › archive › dc_27f43f0f83be

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation — arXiv:2611.04974

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04974
License (as archived)
CC0-1.0
Archived
2026-11-04T21:40:17.043Z
SHA-256 of the archived text
cf88c909db86261b3a2361a2393705e33ae1ab3210c4a9db0401923782445e77
Stable URL of this page
https://metraipolis.com/documento/dc_27f43f0f83be

How to cite

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation — arXiv:2611.04974 — arXiv (en), https://arxiv.org/abs/2611.04974 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27f43f0f83be (Metraipolis archive dc_27f43f0f83be, sha256 cf88c909db86261b3a2361a2393705e33ae1ab3210c4a9db0401923782445e77)
BibTeX
@misc{dc27f43f0f83be,
  title = {LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation — arXiv:2611.04974},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04974},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27f43f0f83be; sha256 cf88c909db86261b3a2361a2393705e33ae1ab3210c4a9db0401923782445e77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04974. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We investigate the automated generation of executable robot reinforcement learning (RL) policies from natural-language task descriptions. Rather than using large language models (LLMs) as execution-time decision makers, we use them as designers that construct RL pipelines before deployment, including Markov decision process (MDP) formulation and simulator implementation. We identify a phase-wise structure in this problem: MDP formulation is dependency-structured and sequential, whereas simulator implementation becomes modular once the formulation is fixed. Based on this structure, we propose ARPG, a dependency-aware agentic framework that performs sequential MDP modeling, localized verification and correction, and simulator-structured implementation while externalizing intermediate artifacts. ARPG targets a key failure mode of automated policy generation: executable code may still yield non-learnable policies when state, action, reward, and termination artifacts are not semantically aligned. Experiments in Isaac Sim show that ARPG improves modeling correctness, environment executability, and policy-generation success compared with monolithic LLM baselines and off-the-shelf agentic systems. Additional demonstrations on custom robotics, standard RL, and engineering-domain MDPs further suggest that the same modeling pipeline can be reused beyond the main benchmark suite.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04974 — 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 2026-11-04T21:35:49.699Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).