Metraipolis › archive › dc_ee31e7a02cd2

Neurosymbolic Embodied Agents — arXiv:2608.16794

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.16794
License (as archived): CC0-1.0
Archived: 2026-10-18T18:07:31.806Z
SHA-256 of the archived text: 311fb8efe14078453e57a9d9809e63aef5429e1343539e897265e1b2a3c7915f
Stable URL of this page: https://metraipolis.com/documento/dc_ee31e7a02cd2

How to cite

Neurosymbolic Embodied Agents — arXiv:2608.16794 — arXiv (en), https://arxiv.org/abs/2608.16794 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee31e7a02cd2 (Metraipolis archive dc_ee31e7a02cd2, sha256 311fb8efe14078453e57a9d9809e63aef5429e1343539e897265e1b2a3c7915f)

BibTeX

@misc{dcee31e7a02cd2,
  title = {Neurosymbolic Embodied Agents — arXiv:2608.16794},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16794},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee31e7a02cd2; sha256 311fb8efe14078453e57a9d9809e63aef5429e1343539e897265e1b2a3c7915f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16794. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning. In the first phase, a vision-language model and exploration harness acquire goal-relevant predicates and instance bindings from egocentric observations and grounded interactions, producing a symbolic initial state. In the second, a PDDL transition model restricts decoding to tokens that extend applicable actions. Monte Carlo tree search then evaluates executable continuations using a domain-independent planning heuristic. The resulting plans are executable by construction under the transition model, with transfer to the environment conditioned on correct visual grounding. On VirtualHome and ALFWorld, open 4B-27B models exceed 90% success in both environments, and our smallest agent substantially outperforms a 27B direct visual policy in each. Constraints and search prove complementary rather than interchangeable: in ALFWorld either alone solves under a third of tasks, whereas their combination solves over 95%. The method also uses several times fewer generated tokens than extended thinking and far fewer model-visible images than direct interaction, and residual failures localize to state acquisition rather than plan generation without any specialized training.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.16794 — 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 2026-10-18T16:29:14.154Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).