{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AMAA3NZG5DWVDC2BIIQ3IIMPKS","short_pith_number":"pith:AMAA3NZG","schema_version":"1.0","canonical_sha256":"03000db726e8ed518b414221b4218f54a03330b689d6f0f95c0061abf58f45d0","source":{"kind":"arxiv","id":"2410.08164","version":1},"attestation_state":"computed","paper":{"title":"Agent S: An Open Agentic Framework that Uses Computers Like a Human","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ang Li, Jiachen Yang, Jiuzhou Han, Saaket Agashe, Shuyu Gan, Xin Eric Wang","submitted_at":"2024-10-10T17:43:51Z","abstract_excerpt":"We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facil"},"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":"2410.08164","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-10T17:43:51Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"08da849107573ced2300f2420c808670e56ef7e33adc5ce4a358b2979e816c5e","abstract_canon_sha256":"e09d0fc3a1d5adad11d24821e5724f0169445f43908085b019b5b3a93da6d032"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:49.638159Z","signature_b64":"C+/M64GA60Wl7HeGn+f/hk9GyLzv+p81UVAU2RepRQ4ZD4WZi25B1sy03q/UtJsLlmqhDqeUNf2psofbdhPVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03000db726e8ed518b414221b4218f54a03330b689d6f0f95c0061abf58f45d0","last_reissued_at":"2026-07-05T09:18:49.637661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:49.637661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent S: An Open Agentic Framework that Uses Computers Like a Human","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ang Li, Jiachen Yang, Jiuzhou Han, Saaket Agashe, Shuyu Gan, Xin Eric Wang","submitted_at":"2024-10-10T17:43:51Z","abstract_excerpt":"We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S aims to address three key challenges in automating computer tasks: acquiring domain-specific knowledge, planning over long task horizons, and handling dynamic, non-uniform interfaces. To this end, Agent S introduces experience-augmented hierarchical planning, which learns from external knowledge search and internal experience retrieval at multiple levels, facil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08164","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/2410.08164/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":"2410.08164","created_at":"2026-07-05T09:18:49.637733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08164v1","created_at":"2026-07-05T09:18:49.637733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08164","created_at":"2026-07-05T09:18:49.637733+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMAA3NZG5DWV","created_at":"2026-07-05T09:18:49.637733+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMAA3NZG5DWVDC2B","created_at":"2026-07-05T09:18:49.637733+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMAA3NZG","created_at":"2026-07-05T09:18:49.637733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13239","citing_title":"ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31270","citing_title":"Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13239","citing_title":"ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":1,"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03530","citing_title":"How Far Are We from Generating Missing Modalities with Foundation Models?","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05157","citing_title":"IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents","ref_index":1,"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":269,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21816","citing_title":"From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24168","citing_title":"MGA: Memory-Driven GUI Agent for Observation-Centric Interaction","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05791","citing_title":"GTA1: GUI Test-time Scaling Agent","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11514","citing_title":"FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05157","citing_title":"IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17419","citing_title":"ARMove: Learning to Predict Human Mobility through Agentic Reasoning","ref_index":57,"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":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02729","citing_title":"Augmenting Interface Usability Heuristics for Reliable Computer-Use Agents","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS","json":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS.json","graph_json":"https://pith.science/api/pith-number/AMAA3NZG5DWVDC2BIIQ3IIMPKS/graph.json","events_json":"https://pith.science/api/pith-number/AMAA3NZG5DWVDC2BIIQ3IIMPKS/events.json","paper":"https://pith.science/paper/AMAA3NZG"},"agent_actions":{"view_html":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS","download_json":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS.json","view_paper":"https://pith.science/paper/AMAA3NZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08164&json=true","fetch_graph":"https://pith.science/api/pith-number/AMAA3NZG5DWVDC2BIIQ3IIMPKS/graph.json","fetch_events":"https://pith.science/api/pith-number/AMAA3NZG5DWVDC2BIIQ3IIMPKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS/action/storage_attestation","attest_author":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS/action/author_attestation","sign_citation":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS/action/citation_signature","submit_replication":"https://pith.science/pith/AMAA3NZG5DWVDC2BIIQ3IIMPKS/action/replication_record"}},"created_at":"2026-07-05T09:18:49.637733+00:00","updated_at":"2026-07-05T09:18:49.637733+00:00"}