Metraipolis › archive › dc_b8b84bb3e82d

Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents — arXiv:2610.00613

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00613
License (as archived)
CC0-1.0
Archived
2026-10-06T12:02:18.535Z
SHA-256 of the archived text
0dd92e700fc3ce2c8ef3b8d7361680c4892a85a2be8ceb1b2d99a58aa8e88bd5
Stable URL of this page
https://metraipolis.com/documento/dc_b8b84bb3e82d

How to cite

Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents — arXiv:2610.00613 — arXiv (en), https://arxiv.org/abs/2610.00613 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b8b84bb3e82d (Metraipolis archive dc_b8b84bb3e82d, sha256 0dd92e700fc3ce2c8ef3b8d7361680c4892a85a2be8ceb1b2d99a58aa8e88bd5)
BibTeX
@misc{dcb8b84bb3e82d,
  title = {Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents — arXiv:2610.00613},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00613},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b8b84bb3e82d; sha256 0dd92e700fc3ce2c8ef3b8d7361680c4892a85a2be8ceb1b2d99a58aa8e88bd5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00613. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial comprehension through an architecture combining geometrical tools with a LLM serving as a high-level orchestrator in grid-world environments. The agent first collects geodesic trajectories, which are then vector-quantized to extract a representative subset. Offline, the LLM associates a natural language description of the underlying behavioral patterns to each selected trajectory, making it a tool. Online, the LLM chooses the appropriate tool conditioned on the current state and goal. Low-level control is handled by primitive actions that execute the trajectory associated with the tool. From an agentic AI perspective, this approach separates learning into two levels: tool discovery is handled through unsupervised quantization of trajectories, while reasoning and decision-making are handled by the LLM. We test the approach in a partially observable dynamic 2D grid environment with an open vision-language model (Qwen3.6-35B-A3B). Pairing the geometry-derived tool library with an agent-centered zoom tool and a collision detection tool lets a fast, non-reasoning configuration match the goal-reaching rate of a much more costly chain-of-thought version, while cutting the cost of a decision from minutes to seconds.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Robotics (cs.RO); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2610.00613 — 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 2026-10-06T10:21:27.873Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).