{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DT2MBQDJCTERKKGRJMQGZRGRYO","short_pith_number":"pith:DT2MBQDJ","schema_version":"1.0","canonical_sha256":"1cf4c0c06914c91528d14b206cc4d1c3ace6a2644ead1dc72e657d3159cd96ad","source":{"kind":"arxiv","id":"2403.03186","version":3},"attestation_state":"computed","paper":{"title":"Cradle: Empowering Foundation Agents Towards General Computer Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Bohan Zhou, B\\\"orje F. Karlsson, Boyu Li, Ceyao Zhang, Chaojie Wang, Chuqiao Zong, Haochong Xia, Jiechuan Jiang, Junpeng Yue, Longtao Zheng, Long Tian, Molei Qin, Pengjie Gu, Ruyi An, Shuicheng Yan, Tianbao Xie, Weihao Tan, Wentao Zhang, Xiaoqiang Chai, Xinrun Wang, Xinrun Xu, Xiyun Li, Yewen Li, Yifei Bi, Yujie Wu, Ziluo Ding, Zongqing Lu","submitted_at":"2024-03-05T18:22:29Z","abstract_excerpt":"Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a prelimina"},"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":"2403.03186","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-05T18:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"1e182df9349b2135a00d680057df3ce7046ca57bd1abc7c39d6e69ec3b52d6c2","abstract_canon_sha256":"c78f4fe161c4431eb9ac9c6bfba51be20bbd08493fc0b070ae6029b5774fbf70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:20.028719Z","signature_b64":"h0JMcz7e02OFRBqnunivcBn0YJM+NB8RLN3CYITGWcWwMFz206ivJJlGqGkoErj63/6MoCBhhrGHdOY/flr5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cf4c0c06914c91528d14b206cc4d1c3ace6a2644ead1dc72e657d3159cd96ad","last_reissued_at":"2026-07-05T08:39:20.028216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:20.028216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cradle: Empowering Foundation Agents Towards General Computer Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bo An, Bohan Zhou, B\\\"orje F. Karlsson, Boyu Li, Ceyao Zhang, Chaojie Wang, Chuqiao Zong, Haochong Xia, Jiechuan Jiang, Junpeng Yue, Longtao Zheng, Long Tian, Molei Qin, Pengjie Gu, Ruyi An, Shuicheng Yan, Tianbao Xie, Weihao Tan, Wentao Zhang, Xiaoqiang Chai, Xinrun Wang, Xinrun Xu, Xiyun Li, Yewen Li, Yifei Bi, Yujie Wu, Ziluo Ding, Zongqing Lu","submitted_at":"2024-03-05T18:22:29Z","abstract_excerpt":"Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a prelimina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03186","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/2403.03186/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":"2403.03186","created_at":"2026-07-05T08:39:20.028276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03186v3","created_at":"2026-07-05T08:39:20.028276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03186","created_at":"2026-07-05T08:39:20.028276+00:00"},{"alias_kind":"pith_short_12","alias_value":"DT2MBQDJCTER","created_at":"2026-07-05T08:39:20.028276+00:00"},{"alias_kind":"pith_short_16","alias_value":"DT2MBQDJCTERKKGR","created_at":"2026-07-05T08:39:20.028276+00:00"},{"alias_kind":"pith_short_8","alias_value":"DT2MBQDJ","created_at":"2026-07-05T08:39:20.028276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19830","citing_title":"JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09826","citing_title":"OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24893","citing_title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29472","citing_title":"Agent-Computer Observation Interfaces Enable Dynamic Computer Use","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27761","citing_title":"AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18652","citing_title":"MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18636","citing_title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00347","citing_title":"Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07429","citing_title":"GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14872","citing_title":"SkillDroid: Compile Once, Reuse Forever","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15671","citing_title":"Long-Term Memory for VLA-based Agents in Open-World Task Execution","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21375","citing_title":"VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO","json":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO.json","graph_json":"https://pith.science/api/pith-number/DT2MBQDJCTERKKGRJMQGZRGRYO/graph.json","events_json":"https://pith.science/api/pith-number/DT2MBQDJCTERKKGRJMQGZRGRYO/events.json","paper":"https://pith.science/paper/DT2MBQDJ"},"agent_actions":{"view_html":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO","download_json":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO.json","view_paper":"https://pith.science/paper/DT2MBQDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03186&json=true","fetch_graph":"https://pith.science/api/pith-number/DT2MBQDJCTERKKGRJMQGZRGRYO/graph.json","fetch_events":"https://pith.science/api/pith-number/DT2MBQDJCTERKKGRJMQGZRGRYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO/action/storage_attestation","attest_author":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO/action/author_attestation","sign_citation":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO/action/citation_signature","submit_replication":"https://pith.science/pith/DT2MBQDJCTERKKGRJMQGZRGRYO/action/replication_record"}},"created_at":"2026-07-05T08:39:20.028276+00:00","updated_at":"2026-07-05T08:39:20.028276+00:00"}