Metraipolis › archive › dc_ad25dead8efe

SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning — arXiv:2610.11223

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.11223
License (as archived): CC0-1.0
Archived: 2026-10-09T05:57:23.506Z
SHA-256 of the archived text: a7d0b94f48d4c4722b111373671115e2bed22757512b4b38aab86dc4e90432a0
Stable URL of this page: https://metraipolis.com/documento/dc_ad25dead8efe

How to cite

SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning — arXiv:2610.11223 — arXiv (en), https://arxiv.org/abs/2610.11223 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ad25dead8efe (Metraipolis archive dc_ad25dead8efe, sha256 a7d0b94f48d4c4722b111373671115e2bed22757512b4b38aab86dc4e90432a0)

BibTeX

@misc{dcad25dead8efe,
  title = {SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning — arXiv:2610.11223},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11223},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ad25dead8efe; sha256 a7d0b94f48d4c4722b111373671115e2bed22757512b4b38aab86dc4e90432a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11223. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations unresolved, reducing planning reliability and wasting inference-time computation. We develop an inference-time monitor that exposes and verifies intermediate plans without disrupting the original decoding trajectory. Building on this monitor, we propose SafeInferCom, a formal verifier-guided framework that preserves valid intermediate plans and directs error correction during generation. Experiments across multiple LRLMs and planning domains reveal reasoning-response inconsistency and limited self-correction under one-shot inference. SafeInferCom improves planning success and accelerates error correction relative to one-shot inference. When combined with iterative refinement, it further improves success while reducing token usage compared with refinement alone. We additionally evaluate SafeInferCom in VirtualHome and provide a real-world robotic-arm demonstration.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Logic in Computer Science (cs.LO).
Pagina del lavoro: https://arxiv.org/abs/2610.11223 — 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 2026-10-09T05:47:01.595Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).