{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4H5ZTYKF5RPLG6ALJOEKTOHGW4","short_pith_number":"pith:4H5ZTYKF","schema_version":"1.0","canonical_sha256":"e1fb99e145ec5eb3780b4b88a9b8e6b712f6392b8db98812a83527065e52c6ea","source":{"kind":"arxiv","id":"2508.04482","version":1},"attestation_state":"computed","paper":{"title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Biao Yi, Fan Wu, Fei Wu, Guoyin Wang, Hongxia Yang, Jiasheng Ye, Jiwei Li, Keting Yin, Kun Kuang, Liang Wang, Meiling Tao, Ruixuan Xiao, Shengyu Zhang, Shengze Xu, Shenzhi Wang, Shuofei Qiao, Tao Xiong, Tieyong Zeng, Wangchunshu Zhou, Xiangxin Zhou, Xinchen Xu, Xueyu Hu, Yuchen Eleanor Jiang, Yuhuai Li, Yurun Chen, Zhaokai Wang, Zhou Zhao, Zishu Wei, Ziyu Zhao","submitted_at":"2025-08-06T14:33:45Z","abstract_excerpt":"The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality, as (M)LLM-based Agents using computing devices (e.g., computers and mobile phones) by operating within the environments and interfaces (e.g., Graphical User Interface (GUI)) provided by operating systems (OS) to automate tasks have significantly advanced. This paper presents a comprehensive survey of these advanced agents, designated as OS Agents. We begin by "},"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":"2508.04482","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-06T14:33:45Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"6650b024c013fbf8c8962a40bfd6da68330f9f89aee20f9517f74b880c9e70f9","abstract_canon_sha256":"ec827e16ee5b0216ec4ad26fa130123ebf85610f53512488ec78540a6573154f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:37.688167Z","signature_b64":"k3b/cK5XVQt0seZGXXn7lOpZcNgZqujcHn5+cun4wjPfrY9LZHpyeecV2o0LcsqVZSduEBwXwiD1Atxs+wGNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1fb99e145ec5eb3780b4b88a9b8e6b712f6392b8db98812a83527065e52c6ea","last_reissued_at":"2026-07-05T11:49:37.687659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:37.687659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Biao Yi, Fan Wu, Fei Wu, Guoyin Wang, Hongxia Yang, Jiasheng Ye, Jiwei Li, Keting Yin, Kun Kuang, Liang Wang, Meiling Tao, Ruixuan Xiao, Shengyu Zhang, Shengze Xu, Shenzhi Wang, Shuofei Qiao, Tao Xiong, Tieyong Zeng, Wangchunshu Zhou, Xiangxin Zhou, Xinchen Xu, Xueyu Hu, Yuchen Eleanor Jiang, Yuhuai Li, Yurun Chen, Zhaokai Wang, Zhou Zhao, Zishu Wei, Ziyu Zhao","submitted_at":"2025-08-06T14:33:45Z","abstract_excerpt":"The dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multi-modal) large language models ((M)LLMs), this dream is closer to reality, as (M)LLM-based Agents using computing devices (e.g., computers and mobile phones) by operating within the environments and interfaces (e.g., Graphical User Interface (GUI)) provided by operating systems (OS) to automate tasks have significantly advanced. This paper presents a comprehensive survey of these advanced agents, designated as OS Agents. We begin by "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04482","kind":"arxiv","version":1},"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/2508.04482/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":"2508.04482","created_at":"2026-07-05T11:49:37.687734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04482v1","created_at":"2026-07-05T11:49:37.687734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04482","created_at":"2026-07-05T11:49:37.687734+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H5ZTYKF5RPL","created_at":"2026-07-05T11:49:37.687734+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H5ZTYKF5RPLG6AL","created_at":"2026-07-05T11:49:37.687734+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H5ZTYKF","created_at":"2026-07-05T11:49:37.687734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14528","citing_title":"Why Johnny Can't Use Agents: Industry Aspirations vs. User Realities with AI Agents","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10139","citing_title":"Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02544","citing_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02729","citing_title":"Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4","json":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4.json","graph_json":"https://pith.science/api/pith-number/4H5ZTYKF5RPLG6ALJOEKTOHGW4/graph.json","events_json":"https://pith.science/api/pith-number/4H5ZTYKF5RPLG6ALJOEKTOHGW4/events.json","paper":"https://pith.science/paper/4H5ZTYKF"},"agent_actions":{"view_html":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4","download_json":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4.json","view_paper":"https://pith.science/paper/4H5ZTYKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04482&json=true","fetch_graph":"https://pith.science/api/pith-number/4H5ZTYKF5RPLG6ALJOEKTOHGW4/graph.json","fetch_events":"https://pith.science/api/pith-number/4H5ZTYKF5RPLG6ALJOEKTOHGW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4/action/storage_attestation","attest_author":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4/action/author_attestation","sign_citation":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4/action/citation_signature","submit_replication":"https://pith.science/pith/4H5ZTYKF5RPLG6ALJOEKTOHGW4/action/replication_record"}},"created_at":"2026-07-05T11:49:37.687734+00:00","updated_at":"2026-07-05T11:49:37.687734+00:00"}