Metraipolis › archive › dc_23df925fd8ca

Structural Inference under Hidden Agents — arXiv:2609.18045

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.18045
License (as archived): CC0-1.0
Archived: 2026-10-15T15:04:33.643Z
SHA-256 of the archived text: ec802f2e476cfb699e49d0d78878c54225f53b4bab82da22c113dcd8d61fe062
Stable URL of this page: https://metraipolis.com/documento/dc_23df925fd8ca

How to cite

Structural Inference under Hidden Agents — arXiv:2609.18045 — arXiv (en), https://arxiv.org/abs/2609.18045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23df925fd8ca (Metraipolis archive dc_23df925fd8ca, sha256 ec802f2e476cfb699e49d0d78878c54225f53b4bab82da22c113dcd8d61fe062)

BibTeX

@misc{dc23df925fd8ca,
  title = {Structural Inference under Hidden Agents — arXiv:2609.18045},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18045},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23df925fd8ca; sha256 ec802f2e476cfb699e49d0d78878c54225f53b4bab82da22c113dcd8d61fe062},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recovering latent interaction structures from multi-agent dynamics is important for understanding and predicting interacting systems. Trajectory-based structural inference has achieved promising performance, but conventional formulations assume that the trajectories of all modeled agents are available. In practice, agents may become unobserved at deployment because of limited sensing, occlusion, or communication failure. Existing studies have considered unseen-node estimation, structural inference under partial observations, and missing-value imputation, yet the joint recovery of hidden-agent trajectories and their interactions remains underexplored. We formulate this problem as structural inference under hidden agents. Its key difficulty is a circular dependency: recovering interactions involving a hidden agent requires an estimate of its trajectory, while trajectory reconstruction can itself benefit from structural information. To address this challenge, we propose Structural Inference under Hidden Agents (SIHA), which combines structure-agnostic initialization with structure-guided iterative refinement. SIHA reconstructs hidden trajectories from visible observations, infers interactions using Neural Relational Inference, and feeds the estimated structure back into hidden-state reconstruction through multi-strength structural attention and iterative state--structure updates. Experiments on three benchmark dynamical systems demonstrate consistent improvements in visible-to-visible structural inference, while also showing benefits in hidden-state reconstruction and future prediction. Motion-capture experiments with simulated whole-limb occlusion further demonstrate its effectiveness in realistic hidden-agent settings.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.18045 — 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 2026-10-15T14:08:19.096Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).