{"paper":{"title":"NOEM$^{3}$A: a Neuro-symbolic Ontology-Enhanced Method for Multi-intent understanding in Mobile Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aifen Sui, Ioannis Tzachristas","submitted_at":"2025-11-24T23:14:45Z","abstract_excerpt":"Mobile agents must map natural-language requests to executable intents under tight latency and privacy constraints. Scaling the language model is often an inefficient way to improve this component. We present NOEM$^{3}$A, a lightweight neuro-symbolic layer that augments compact language models with an intent ontology. For each query, NOEM$^{3}$A retrieves a small ontology neighborhood, injects candidate action labels into the prompt and applies a token-level decoding prior toward valid labels. This injects symbolic intent structure into both input and output representations while keeping infer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.19780","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.19780/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}