{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XTKVQBFF47TTBMTHHDUK3MKVA7","short_pith_number":"pith:XTKVQBFF","schema_version":"1.0","canonical_sha256":"bcd55804a5e7e730b26738e8adb15507cde4b454a97a9e49d5ae55640326940a","source":{"kind":"arxiv","id":"2411.00820","version":1},"attestation_state":"computed","paper":{"title":"AutoGLM: Autonomous Foundation Agents for GUIs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.HC","authors_text":"Bo Qin, Dongzhu Liang, Guang Dong, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Iat Long Iong, Jiadai Sun, Jiaqi Wang, Jie Tang, Junjie Gao, Junjun Shan, Kangning Liu, Shudan Zhang, Shuntian Yao, Siyi Cheng, Wentao Yao, Wenyi Zhao, Xiao Liu, Xinghan Liu, Xinyi Liu, Xinying Chen, Xinyue Yang, Yang Yang, Yifan Xu, Yujia Wang, Yulin Xu, Yuxiao Dong, Yu Yang, Zehan Qi","submitted_at":"2024-10-28T17:05:10Z","abstract_excerpt":"We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representa"},"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":"2411.00820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-10-28T17:05:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"741b058bd1a2a20abbe345d9b4d10ebae35dce60a0cad9b03d28a4d936e4e3d0","abstract_canon_sha256":"16cf90ceaafe9ddbebd389b12e481c8c6c2432c5654e5430c3b8a0d0739cd841"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:51.029448Z","signature_b64":"MYIgIKcuaGeN0DwRC66khbHeoS64NEjXcwSvrS6ofIi8dziOwKgNoKKsVM2IPMcLJTMZDueSs2ih/VoWvViRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd55804a5e7e730b26738e8adb15507cde4b454a97a9e49d5ae55640326940a","last_reissued_at":"2026-07-05T09:29:51.028848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:51.028848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoGLM: Autonomous Foundation Agents for GUIs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.HC","authors_text":"Bo Qin, Dongzhu Liang, Guang Dong, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Iat Long Iong, Jiadai Sun, Jiaqi Wang, Jie Tang, Junjie Gao, Junjun Shan, Kangning Liu, Shudan Zhang, Shuntian Yao, Siyi Cheng, Wentao Yao, Wenyi Zhao, Xiao Liu, Xinghan Liu, Xinyi Liu, Xinying Chen, Xinyue Yang, Yang Yang, Yifan Xu, Yujia Wang, Yulin Xu, Yuxiao Dong, Yu Yang, Zehan Qi","submitted_at":"2024-10-28T17:05:10Z","abstract_excerpt":"We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00820","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/2411.00820/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":"2411.00820","created_at":"2026-07-05T09:29:51.028907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00820v1","created_at":"2026-07-05T09:29:51.028907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00820","created_at":"2026-07-05T09:29:51.028907+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTKVQBFF47TT","created_at":"2026-07-05T09:29:51.028907+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTKVQBFF47TTBMTH","created_at":"2026-07-05T09:29:51.028907+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTKVQBFF","created_at":"2026-07-05T09:29:51.028907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10522","citing_title":"GUI-AC: Enhancing Continual Learning in GUI Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09447","citing_title":"AliyunConsoleAgent: Training Web Agents in Real-World Cloud Environments via Distillation and Reinforcement Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31410","citing_title":"Xiaomi-GUI-0 Technical Report","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00333","citing_title":"(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27944","citing_title":"It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31410","citing_title":"Xiaomi-GUI-0 Technical Report","ref_index":20,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29537","citing_title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29705","citing_title":"GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28646","citing_title":"MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18048","citing_title":"DocOS: Towards Proactive Document-Guided Actions in GUI Agents","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19396","citing_title":"EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10139","citing_title":"Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22942","citing_title":"ClawMobile: Rethinking Smartphone-Native Agentic Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12481","citing_title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07630","citing_title":"Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":13,"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":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7","json":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7.json","graph_json":"https://pith.science/api/pith-number/XTKVQBFF47TTBMTHHDUK3MKVA7/graph.json","events_json":"https://pith.science/api/pith-number/XTKVQBFF47TTBMTHHDUK3MKVA7/events.json","paper":"https://pith.science/paper/XTKVQBFF"},"agent_actions":{"view_html":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7","download_json":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7.json","view_paper":"https://pith.science/paper/XTKVQBFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00820&json=true","fetch_graph":"https://pith.science/api/pith-number/XTKVQBFF47TTBMTHHDUK3MKVA7/graph.json","fetch_events":"https://pith.science/api/pith-number/XTKVQBFF47TTBMTHHDUK3MKVA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7/action/storage_attestation","attest_author":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7/action/author_attestation","sign_citation":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7/action/citation_signature","submit_replication":"https://pith.science/pith/XTKVQBFF47TTBMTHHDUK3MKVA7/action/replication_record"}},"created_at":"2026-07-05T09:29:51.028907+00:00","updated_at":"2026-07-05T09:29:51.028907+00:00"}