{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B6G4LGJ7ILC7IB4K77H6JMJGK5","short_pith_number":"pith:B6G4LGJ7","schema_version":"1.0","canonical_sha256":"0f8dc5993f42c5f4078affcfe4b12657677c0b4f88033e94266f1c1567e03c1b","source":{"kind":"arxiv","id":"2402.07456","version":2},"attestation_state":"computed","paper":{"title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengcheng Han, Lingpeng Kong, Shunyu Yao, Tao Yu, Zhenmin Weng, Zhiyong Wu, Zhoumianze Liu, Zichen Ding","submitted_at":"2024-02-12T07:29:22Z","abstract_excerpt":"Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerated progress in building digital agents. However, most of these agents are designed to interact with a narrow domain, such as a specific software or website. This narrow focus constrains their applicability for general computer tasks. To this end, we introduce OS-Copilot, a framework to build generalist agents capable of interfacing with comprehensive elements in an operating system (OS), including the web, code termi"},"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":"2402.07456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-12T07:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"27bba2042f85ca3bcaa28d5d789ad5a055bb4128fedc803d8827bb7ed6902eb4","abstract_canon_sha256":"b7273a904f4e57965635226f0581bdb5cb3ee75854d72ac7a5b469a0323e6c61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:33.454365Z","signature_b64":"z0OkgVaGGYF+sKfTJqK51jxT0Hcyhza2ImbmiC9JHMJGtPYVyGLIkn7eg5iRxPeerHImDlQgb86zIGClpMzaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f8dc5993f42c5f4078affcfe4b12657677c0b4f88033e94266f1c1567e03c1b","last_reissued_at":"2026-07-05T07:45:33.453856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:33.453856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OS-Copilot: Towards Generalist Computer Agents with Self-Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengcheng Han, Lingpeng Kong, Shunyu Yao, Tao Yu, Zhenmin Weng, Zhiyong Wu, Zhoumianze Liu, Zichen Ding","submitted_at":"2024-02-12T07:29:22Z","abstract_excerpt":"Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerated progress in building digital agents. However, most of these agents are designed to interact with a narrow domain, such as a specific software or website. This narrow focus constrains their applicability for general computer tasks. To this end, we introduce OS-Copilot, a framework to build generalist agents capable of interfacing with comprehensive elements in an operating system (OS), including the web, code termi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07456","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/2402.07456/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":"2402.07456","created_at":"2026-07-05T07:45:33.453924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07456v2","created_at":"2026-07-05T07:45:33.453924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07456","created_at":"2026-07-05T07:45:33.453924+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6G4LGJ7ILC7","created_at":"2026-07-05T07:45:33.453924+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6G4LGJ7ILC7IB4K","created_at":"2026-07-05T07:45:33.453924+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6G4LGJ7","created_at":"2026-07-05T07:45:33.453924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17929","citing_title":"PreAct: Computer-Using Agents that Get Faster on Repeated Tasks","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13239","citing_title":"ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01709","citing_title":"COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13239","citing_title":"ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25160","citing_title":"ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis","ref_index":4,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29115","citing_title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","ref_index":11,"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":172,"is_internal_anchor":false},{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":270,"is_internal_anchor":false},{"citing_arxiv_id":"2505.10887","citing_title":"InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18535","citing_title":"Beyond Scaling: Agents Are Heading to the Edge","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19762","citing_title":"What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19662","citing_title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03486","citing_title":"VisionClaw: Always-On AI Agents through Smart Glasses","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2405.14573","citing_title":"AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11943","citing_title":"ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08224","citing_title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","ref_index":159,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14872","citing_title":"SkillDroid: Compile Once, Reuse Forever","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15136","citing_title":"Feedback-Driven Execution for LLM-Based Binary Analysis","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5","json":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5.json","graph_json":"https://pith.science/api/pith-number/B6G4LGJ7ILC7IB4K77H6JMJGK5/graph.json","events_json":"https://pith.science/api/pith-number/B6G4LGJ7ILC7IB4K77H6JMJGK5/events.json","paper":"https://pith.science/paper/B6G4LGJ7"},"agent_actions":{"view_html":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5","download_json":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5.json","view_paper":"https://pith.science/paper/B6G4LGJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07456&json=true","fetch_graph":"https://pith.science/api/pith-number/B6G4LGJ7ILC7IB4K77H6JMJGK5/graph.json","fetch_events":"https://pith.science/api/pith-number/B6G4LGJ7ILC7IB4K77H6JMJGK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5/action/storage_attestation","attest_author":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5/action/author_attestation","sign_citation":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5/action/citation_signature","submit_replication":"https://pith.science/pith/B6G4LGJ7ILC7IB4K77H6JMJGK5/action/replication_record"}},"created_at":"2026-07-05T07:45:33.453924+00:00","updated_at":"2026-07-05T07:45:33.453924+00:00"}