{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U52HJF5X3S2Y5YYA7AMDNQWBT6","short_pith_number":"pith:U52HJF5X","schema_version":"1.0","canonical_sha256":"a7747497b7dcb58ee300f81836c2c19fa02c0816cd85e5ee56242316ae7e274c","source":{"kind":"arxiv","id":"2607.01084","version":1},"attestation_state":"computed","paper":{"title":"Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Weiming Wu, Zi-Jian Cheng","submitted_at":"2026-07-01T15:40:25Z","abstract_excerpt":"While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics. To address this generalization gap, we formalize OpenAgent (Tool-Use Agent in Open-World), a problem setting characterized by distributional shifts across query, action, observation, and domain dimensions. To systematically diagnose its impact, we construct a controlled sandbox environment where we define fine-grained environmental shifts across a four-tier hierarchy, Perception, In"},"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":"2607.01084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-01T15:40:25Z","cross_cats_sorted":[],"title_canon_sha256":"a12f9f38147ddd4e9626c7482b72a90224c2175f1d0947824b7be516ce7cd11a","abstract_canon_sha256":"36d5c38c956ca61f54ffdd3cec4cec8a5cbd69a7d48c23ed7b2ab24be40102f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:28.282294Z","signature_b64":"VeywCisOBE0kVtKqePVU0SiDrUc15fg7E2VWkNU68eA9b/FRwJZ/fsV7+hR+qjhBw5C1HY+sIgw+tDVWffWCCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7747497b7dcb58ee300f81836c2c19fa02c0816cd85e5ee56242316ae7e274c","last_reissued_at":"2026-07-02T01:18:28.281845Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:28.281845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Weiming Wu, Zi-Jian Cheng","submitted_at":"2026-07-01T15:40:25Z","abstract_excerpt":"While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics. To address this generalization gap, we formalize OpenAgent (Tool-Use Agent in Open-World), a problem setting characterized by distributional shifts across query, action, observation, and domain dimensions. To systematically diagnose its impact, we construct a controlled sandbox environment where we define fine-grained environmental shifts across a four-tier hierarchy, Perception, In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01084","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/2607.01084/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":"2607.01084","created_at":"2026-07-02T01:18:28.281921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01084v1","created_at":"2026-07-02T01:18:28.281921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01084","created_at":"2026-07-02T01:18:28.281921+00:00"},{"alias_kind":"pith_short_12","alias_value":"U52HJF5X3S2Y","created_at":"2026-07-02T01:18:28.281921+00:00"},{"alias_kind":"pith_short_16","alias_value":"U52HJF5X3S2Y5YYA","created_at":"2026-07-02T01:18:28.281921+00:00"},{"alias_kind":"pith_short_8","alias_value":"U52HJF5X","created_at":"2026-07-02T01:18:28.281921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6","json":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6.json","graph_json":"https://pith.science/api/pith-number/U52HJF5X3S2Y5YYA7AMDNQWBT6/graph.json","events_json":"https://pith.science/api/pith-number/U52HJF5X3S2Y5YYA7AMDNQWBT6/events.json","paper":"https://pith.science/paper/U52HJF5X"},"agent_actions":{"view_html":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6","download_json":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6.json","view_paper":"https://pith.science/paper/U52HJF5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01084&json=true","fetch_graph":"https://pith.science/api/pith-number/U52HJF5X3S2Y5YYA7AMDNQWBT6/graph.json","fetch_events":"https://pith.science/api/pith-number/U52HJF5X3S2Y5YYA7AMDNQWBT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6/action/storage_attestation","attest_author":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6/action/author_attestation","sign_citation":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6/action/citation_signature","submit_replication":"https://pith.science/pith/U52HJF5X3S2Y5YYA7AMDNQWBT6/action/replication_record"}},"created_at":"2026-07-02T01:18:28.281921+00:00","updated_at":"2026-07-02T01:18:28.281921+00:00"}