Metraipolis › archive › dc_da849b4adacc
CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders — arXiv:2610.07868
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07868
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:07:20.064Z
- SHA-256 of the archived text
ebab2119a1027748186604637b44704560df772df049bd89c8171b3b8896d9ff- Stable URL of this page
https://metraipolis.com/documento/dc_da849b4adacc
How to cite
CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders — arXiv:2610.07868 — arXiv (en), https://arxiv.org/abs/2610.07868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da849b4adacc (Metraipolis archive dc_da849b4adacc, sha256 ebab2119a1027748186604637b44704560df772df049bd89c8171b3b8896d9ff)
BibTeX
@misc{dcda849b4adacc,
title = {CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders — arXiv:2610.07868},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07868},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da849b4adacc; sha256 ebab2119a1027748186604637b44704560df772df049bd89c8171b3b8896d9ff},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language model agents have been used to search over symbolic structures such as programs and equations. We propose CueRator, an agentic framework for policy-aware decision-rule discovery, which adapts frozen contrastive multimodal encoders by searching for the decision rule that converts their cross-modal similarities into predictions. We validate it on open-vocabulary audio-visual event perception, where existing methods involve a trade-off between adaptivity and generalization to unseen categories: trained modules adapt at the cost of generalization, and fixed rules the reverse. The framework pairs a symbolic formulation for generalization with a lightweight policy that predicts its parameters per video for adaptivity. A report-guided multi-agent loop discovers the formulation offline, evaluating each candidate on its expressive ceiling and on whether a trained policy can realize it. On OV-AVEBench, CueRator raises the total average from 57.8 to 60.2 and unseen-category performance from 55.8 to 59.9 over the best existing method, reducing the seen-unseen gap from 7.1 to 1.2. Ablations attribute the gains to both the formulation and the policy and show that both feedback signals are necessary for effective search. CueRator also improves over the respective baselines on two further audio-visual event perception tasks, and the discovered rule remains competitive across encoders with only the policy retrained. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.07868 — 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 2026-10-07T12:37:32.921Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).