{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AO6BK5V74MJ4CT5CUTUPHZTKEB","short_pith_number":"pith:AO6BK5V7","schema_version":"1.0","canonical_sha256":"03bc1576bfe313c14fa2a4e8f3e66a207c3ddae444676165c3d5d5068eb6ca29","source":{"kind":"arxiv","id":"2604.06995","version":2},"attestation_state":"computed","paper":{"title":"What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Yi, Huajun Chen, Songze Li, Tianqi Liu, Wen Zhang, Xiaoke Guo, Zhaoyan Gong, Zhiqiang Liu","submitted_at":"2026-04-08T12:12:09Z","abstract_excerpt":"Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making, which lacks interpretability and overlooks a comprehensive understanding of UI elements, ultimately leading to task failure. To enhance the understanding and interaction with UIs, we propose an innovative GUI reasoning paradigm called UI-in-the-Loop (UILoop). Our approach treats the GUI reasoning task as a cyclic Screen-UI elements-Action process. By enabling Multimodal Large Language Models (MLLMs) to explicitly le"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.06995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-08T12:12:09Z","cross_cats_sorted":[],"title_canon_sha256":"e1c36b436ae993ba052abaa403f4afc28f0e3a81eaef99b709c1dfe563392e99","abstract_canon_sha256":"d855ca8afa8f69d148a7dc780e8dbdad764e529552e63863fcb918193d6ace74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:46.790770Z","signature_b64":"xLep8s94IOKOMB3GdnIrENPUk/z0WXLqE1RuP/q/DgTiuThCmPnJIH74jKB6ke2+7CZaLxRvR4543TbaKDq3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03bc1576bfe313c14fa2a4e8f3e66a207c3ddae444676165c3d5d5068eb6ca29","last_reissued_at":"2026-06-02T01:03:46.790309Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:46.790309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Yi, Huajun Chen, Songze Li, Tianqi Liu, Wen Zhang, Xiaoke Guo, Zhaoyan Gong, Zhiqiang Liu","submitted_at":"2026-04-08T12:12:09Z","abstract_excerpt":"Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making, which lacks interpretability and overlooks a comprehensive understanding of UI elements, ultimately leading to task failure. To enhance the understanding and interaction with UIs, we propose an innovative GUI reasoning paradigm called UI-in-the-Loop (UILoop). Our approach treats the GUI reasoning task as a cyclic Screen-UI elements-Action process. By enabling Multimodal Large Language Models (MLLMs) to explicitly le"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By enabling Multimodal Large Language Models (MLLMs) to explicitly learn the localization, semantic functions, and practical usage of key UI elements, UILoop achieves precise element discovery and performs interpretable reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That inserting an explicit UI-element learning step into a cyclic Screen-UI-Action process will produce both higher accuracy and better interpretability in MLLMs, without the added structure introducing new failure modes or requiring impractical amounts of supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UI-in-the-Loop makes multimodal models explicitly learn UI element locations, meanings, and uses in a cyclic screen-element-action loop, delivering better UI comprehension and GUI reasoning on a new 26K-sample benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f61b6607d65f8abf67e5db36beb8920582745aafd00371cdb75d138cdfbbaf70"},"source":{"id":"2604.06995","kind":"arxiv","version":2},"verdict":{"id":"9d8eb0a4-40fe-44a5-8b4e-6af8b96256a5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:40:58.055768Z","strongest_claim":"By enabling Multimodal Large Language Models (MLLMs) to explicitly learn the localization, semantic functions, and practical usage of key UI elements, UILoop achieves precise element discovery and performs interpretable reasoning.","one_line_summary":"UI-in-the-Loop makes multimodal models explicitly learn UI element locations, meanings, and uses in a cyclic screen-element-action loop, delivering better UI comprehension and GUI reasoning on a new 26K-sample benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That inserting an explicit UI-element learning step into a cyclic Screen-UI-Action process will produce both higher accuracy and better interpretability in MLLMs, without the added structure introducing new failure modes or requiring impractical amounts of supervision.","pith_extraction_headline":"Treating GUI reasoning as a cyclic Screen-UI-Action process lets MLLMs explicitly learn element localization, semantics, and usage for more precise and interpretable decisions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.06995/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.06995","created_at":"2026-06-02T01:03:46.790381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.06995v2","created_at":"2026-06-02T01:03:46.790381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06995","created_at":"2026-06-02T01:03:46.790381+00:00"},{"alias_kind":"pith_short_12","alias_value":"AO6BK5V74MJ4","created_at":"2026-06-02T01:03:46.790381+00:00"},{"alias_kind":"pith_short_16","alias_value":"AO6BK5V74MJ4CT5C","created_at":"2026-06-02T01:03:46.790381+00:00"},{"alias_kind":"pith_short_8","alias_value":"AO6BK5V7","created_at":"2026-06-02T01:03:46.790381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.21806","citing_title":"TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB","json":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB.json","graph_json":"https://pith.science/api/pith-number/AO6BK5V74MJ4CT5CUTUPHZTKEB/graph.json","events_json":"https://pith.science/api/pith-number/AO6BK5V74MJ4CT5CUTUPHZTKEB/events.json","paper":"https://pith.science/paper/AO6BK5V7"},"agent_actions":{"view_html":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB","download_json":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB.json","view_paper":"https://pith.science/paper/AO6BK5V7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.06995&json=true","fetch_graph":"https://pith.science/api/pith-number/AO6BK5V74MJ4CT5CUTUPHZTKEB/graph.json","fetch_events":"https://pith.science/api/pith-number/AO6BK5V74MJ4CT5CUTUPHZTKEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB/action/storage_attestation","attest_author":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB/action/author_attestation","sign_citation":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB/action/citation_signature","submit_replication":"https://pith.science/pith/AO6BK5V74MJ4CT5CUTUPHZTKEB/action/replication_record"}},"created_at":"2026-06-02T01:03:46.790381+00:00","updated_at":"2026-06-02T01:03:46.790381+00:00"}