{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UDNVVUNWW3ZAP3WHXE3XALEEZM","short_pith_number":"pith:UDNVVUNW","schema_version":"1.0","canonical_sha256":"a0db5ad1b6b6f207eec7b937702c84cb237e46df55d62ba9a0a74459e8ee56fd","source":{"kind":"arxiv","id":"2503.16465","version":3},"attestation_state":"computed","paper":{"title":"OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aston Zhang, Gongshen Liu, Pengzhou Cheng, Zheng Wu, Zhuosheng Zhang, Zongru Wu","submitted_at":"2025-02-26T12:31:16Z","abstract_excerpt":"Autonomous graphical user interface (GUI) agents powered by multimodal large language models have shown great promise. However, a critical yet underexplored issue persists: over-execution, where the agent executes tasks in a fully autonomous way, without adequate assessment of its action confidence to compromise an adaptive human-agent collaboration. This poses substantial risks in complex scenarios, such as those involving ambiguous user instructions, unexpected interruptions, and environmental hijacks. To address the issue, we introduce OS-Kairos, an adaptive GUI agent capable of predicting "},"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":"2503.16465","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-02-26T12:31:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13dfc1595368d2c8b01ee1f7226b31f2a7d28aeb1271feffd3574a9e5ae3e374","abstract_canon_sha256":"4bbffe2c704a3208d4af3cfc3821839c3e4b1644b95c449792a20aba8542a9a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:29.750361Z","signature_b64":"xZAzLJfTPsWVgsgmMntv4fb+X1FXVAMqDFG7TwYf5UfUt11TdgDVGNsDgtzZoBKHUj3x5BuCfDyYiGxqRbDjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0db5ad1b6b6f207eec7b937702c84cb237e46df55d62ba9a0a74459e8ee56fd","last_reissued_at":"2026-07-05T11:36:29.749908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:29.749908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aston Zhang, Gongshen Liu, Pengzhou Cheng, Zheng Wu, Zhuosheng Zhang, Zongru Wu","submitted_at":"2025-02-26T12:31:16Z","abstract_excerpt":"Autonomous graphical user interface (GUI) agents powered by multimodal large language models have shown great promise. However, a critical yet underexplored issue persists: over-execution, where the agent executes tasks in a fully autonomous way, without adequate assessment of its action confidence to compromise an adaptive human-agent collaboration. This poses substantial risks in complex scenarios, such as those involving ambiguous user instructions, unexpected interruptions, and environmental hijacks. To address the issue, we introduce OS-Kairos, an adaptive GUI agent capable of predicting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16465","kind":"arxiv","version":3},"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/2503.16465/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":"2503.16465","created_at":"2026-07-05T11:36:29.749961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16465v3","created_at":"2026-07-05T11:36:29.749961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16465","created_at":"2026-07-05T11:36:29.749961+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDNVVUNWW3ZA","created_at":"2026-07-05T11:36:29.749961+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDNVVUNWW3ZAP3WH","created_at":"2026-07-05T11:36:29.749961+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDNVVUNW","created_at":"2026-07-05T11:36:29.749961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28629","citing_title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2508.19679","citing_title":"InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM","json":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM.json","graph_json":"https://pith.science/api/pith-number/UDNVVUNWW3ZAP3WHXE3XALEEZM/graph.json","events_json":"https://pith.science/api/pith-number/UDNVVUNWW3ZAP3WHXE3XALEEZM/events.json","paper":"https://pith.science/paper/UDNVVUNW"},"agent_actions":{"view_html":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM","download_json":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM.json","view_paper":"https://pith.science/paper/UDNVVUNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16465&json=true","fetch_graph":"https://pith.science/api/pith-number/UDNVVUNWW3ZAP3WHXE3XALEEZM/graph.json","fetch_events":"https://pith.science/api/pith-number/UDNVVUNWW3ZAP3WHXE3XALEEZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM/action/storage_attestation","attest_author":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM/action/author_attestation","sign_citation":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM/action/citation_signature","submit_replication":"https://pith.science/pith/UDNVVUNWW3ZAP3WHXE3XALEEZM/action/replication_record"}},"created_at":"2026-07-05T11:36:29.749961+00:00","updated_at":"2026-07-05T11:36:29.749961+00:00"}