Metraipolis › archive › dc_ab4930b37587
DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds? — arXiv:2611.04228
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04228
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:27:44.431Z
- SHA-256 of the archived text
e464ee851df31ea647c37e3096bec12969f6091441b37b918fec285ec8abc133- Stable URL of this page
https://metraipolis.com/documento/dc_ab4930b37587
How to cite
DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds? — arXiv:2611.04228 — arXiv (en), https://arxiv.org/abs/2611.04228 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab4930b37587 (Metraipolis archive dc_ab4930b37587, sha256 e464ee851df31ea647c37e3096bec12969f6091441b37b918fec285ec8abc133)
BibTeX
@misc{dcab4930b37587,
title = {DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds? — arXiv:2611.04228},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04228},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab4930b37587; sha256 e464ee851df31ea647c37e3096bec12969f6091441b37b918fec285ec8abc133},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04228. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent multimodal agents have shown promising progress in embodied planning and web interaction. However, existing evaluations often rely on simplified tasks with limited combinatorial structure, leaving it unclear whether current agents can robustly integrate perception and reasoning for multi-goal planning under temporal, physical, and multimodal constraints. We introduce DualWorldBench, a unified benchmark for evaluating agent planning under controlled symbolic--temporal and grounded--topological complexity. Built around a shared pickup--delivery interface, DualWorldBench consists of three complementary components: TextWorld, which isolates symbolic planning under varying task compositions and release dynamics; SimWorld, which evaluates grounded path planning under controlled topological variation with text, image, or multimodal inputs; and DualWorld-VQA, a diagnostic suite spanning perception, scene understanding, and planning. Experiments reveal a common gap between local understanding and globally consistent planning. In TextWorld, agents struggle to derive optimal task sequences under interacting temporal constraints; in SimWorld, grounded observations are not reliably converted into feasible action sequences. DualWorld-VQA further confirms that perception and topology understanding do not necessarily translate into constrained planning. Together, these results identify the central challenge as composing symbolic or grounded evidence into globally feasible and efficient multi-goal plans. These findings establish DualWorldBench as a challenging testbed for agents with tighter perception--reasoning--planning integration. All datasets and code are publicly available at our project website this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04228 — 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 2026-11-04T12:26:47.134Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).