Metraipolis › archive › dc_da73d02e6c64
D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models — arXiv:2611.03622
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03622
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:09:20.247Z
- SHA-256 of the archived text
fd554b444df9b04b4ef2d6c226ab8201928c3f38ec6ea54923406dbd95386909- Stable URL of this page
https://metraipolis.com/documento/dc_da73d02e6c64
How to cite
D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models — arXiv:2611.03622 — arXiv (en), https://arxiv.org/abs/2611.03622 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da73d02e6c64 (Metraipolis archive dc_da73d02e6c64, sha256 fd554b444df9b04b4ef2d6c226ab8201928c3f38ec6ea54923406dbd95386909)
BibTeX
@misc{dcda73d02e6c64,
title = {D&A: Decoupling Description and Assessment Enables VLMs as Zero-Shot Robotic Reward Models — arXiv:2611.03622},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03622},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da73d02e6c64; sha256 fd554b444df9b04b4ef2d6c226ab8201928c3f38ec6ea54923406dbd95386909},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03622. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, hallucinating progress in failed executions due to implicit success assumptions or relative temporal ranking designs. Naive prompting of frontier models collapses into a binary success detector that fails to capture nuanced, non-linear progress and failures. While post-training approaches can mitigate this through explicit training, they demand expensive real-world robotics data and require computationally intensive post-training for every individual base model. To resolve these limitations, we introduce D&A (Describe & Assess): our approach decouples progress estimation into an objective, task-grounded textual description of scene dynamics followed by an assessment phase using explicit rubrics. By compelling the VLM to synthesize an explicit, text-based definition of absolute success before scoring, the framework anchors evaluations to an external, global criterion rather than the video's internal timeline. Empirical results demonstrate that our method calibrates zero-shot estimates and mitigates confirmation bias, providing fine-grained, partial progress metrics that accurately penalize failed executions while correctly interpolating successful runs. Being purely prompt-based, D&A generalizes across tasks, embodiments, and benchmarks---matching or surpassing post-trained reward models---and its reward estimates enable efficient downstream reinforcement learning. 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); Machine Learning (cs.LG); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2611.03622 — 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 2026-11-03T10:59:46.181Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).