{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5URKEP6DGKOL4ZDUDVPS6W6C2","short_pith_number":"pith:F5URKEP6","schema_version":"1.0","canonical_sha256":"2f691511fe1994e5f323a0eaf97ade169aa55e96207219b30960dc81340c90ec","source":{"kind":"arxiv","id":"2606.10577","version":1},"attestation_state":"computed","paper":{"title":"AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changze Li, Hantian Shi, Jiaying Luo, Jiyuan Cai, Ming Yang, Tong Qin, Yijian Li","submitted_at":"2026-06-09T08:43:05Z","abstract_excerpt":"Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs). However, existing methods typically rely on learned waypoint predictors to propose navigable actions. This severely limits the model's action space and fails to leverage depth inputs effectively. Moreover, memory is commonly handled by accumulating long textual or visual histories with substantial irrelevant context, or by retrieving cross-episode experiences, which weakens the zero-shot setting. In this paper, we rethink zero-shot VLN-CE as an age"},"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":"2606.10577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-09T08:43:05Z","cross_cats_sorted":[],"title_canon_sha256":"501658319bc4020a097bc0f4625293f534242cb4ee05180102ea8e770cf96c73","abstract_canon_sha256":"4dad3fc35feba1cb8c47aa8f459c6df4b6e6e54cbbb29a3ee6297f40a531a31a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:27.685630Z","signature_b64":"LVD9BnY428OZV3t3XR4gyors5t4stbJpI/7thwFsYs+0NS/o4Xss95Jb7YF2V86lpn6UMnYi4th1eOM23GtNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f691511fe1994e5f323a0eaf97ade169aa55e96207219b30960dc81340c90ec","last_reissued_at":"2026-06-10T01:10:27.684623Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:27.684623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Changze Li, Hantian Shi, Jiaying Luo, Jiyuan Cai, Ming Yang, Tong Qin, Yijian Li","submitted_at":"2026-06-09T08:43:05Z","abstract_excerpt":"Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs). However, existing methods typically rely on learned waypoint predictors to propose navigable actions. This severely limits the model's action space and fails to leverage depth inputs effectively. Moreover, memory is commonly handled by accumulating long textual or visual histories with substantial irrelevant context, or by retrieving cross-episode experiences, which weakens the zero-shot setting. In this paper, we rethink zero-shot VLN-CE as an age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10577","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/2606.10577/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":"2606.10577","created_at":"2026-06-10T01:10:27.684801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10577v1","created_at":"2026-06-10T01:10:27.684801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10577","created_at":"2026-06-10T01:10:27.684801+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5URKEP6DGKO","created_at":"2026-06-10T01:10:27.684801+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5URKEP6DGKOL4ZD","created_at":"2026-06-10T01:10:27.684801+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5URKEP6","created_at":"2026-06-10T01:10:27.684801+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/F5URKEP6DGKOL4ZDUDVPS6W6C2","json":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2.json","graph_json":"https://pith.science/api/pith-number/F5URKEP6DGKOL4ZDUDVPS6W6C2/graph.json","events_json":"https://pith.science/api/pith-number/F5URKEP6DGKOL4ZDUDVPS6W6C2/events.json","paper":"https://pith.science/paper/F5URKEP6"},"agent_actions":{"view_html":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2","download_json":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2.json","view_paper":"https://pith.science/paper/F5URKEP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10577&json=true","fetch_graph":"https://pith.science/api/pith-number/F5URKEP6DGKOL4ZDUDVPS6W6C2/graph.json","fetch_events":"https://pith.science/api/pith-number/F5URKEP6DGKOL4ZDUDVPS6W6C2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2/action/storage_attestation","attest_author":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2/action/author_attestation","sign_citation":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2/action/citation_signature","submit_replication":"https://pith.science/pith/F5URKEP6DGKOL4ZDUDVPS6W6C2/action/replication_record"}},"created_at":"2026-06-10T01:10:27.684801+00:00","updated_at":"2026-06-10T01:10:27.684801+00:00"}