{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RGCY2RZ2YEPFTL5TSE3DPDWSVG","short_pith_number":"pith:RGCY2RZ2","schema_version":"1.0","canonical_sha256":"89858d473ac11e59afb39136378ed2a99bdd12245f73e5bba1935c47f8aeb213","source":{"kind":"arxiv","id":"2607.26148","version":1},"attestation_state":"computed","paper":{"title":"Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gengze Zhou, Jiajun Liu, Jian Zhou, Qi Wu, Sihao Lin, Xunyi Zhao, Zerui Li","submitted_at":"2026-07-28T18:00:34Z","abstract_excerpt":"Autonomous embodied agents must sustain a long decision-making loop that involves perceiving, acting, verifying, and self-correcting over many steps. Current systems sustain this loop through task-specific workflows or embodied policies. We study a third form, agentic embodied control, in which a general-purpose agent holds the loop itself. Using zero-shot navigation as a controlled testbed, we evaluate three software-engineering agent harnesses given only a monocular RGB camera and discrete actions. Under this strictly minimal condition, replicated default-effort configurations reach 70.7$\\pm"},"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":"2607.26148","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-28T18:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"460de77314d3bb8f6708468c32048f038bc5df0738ec7e55e465b1e6fa9f4418","abstract_canon_sha256":"827a1e5c6de020de9b6ca5879fda9f40fb3e53afb2c8ad39f0f88e8e6a43ca02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89858d473ac11e59afb39136378ed2a99bdd12245f73e5bba1935c47f8aeb213","last_reissued_at":"2026-07-30T00:08:28.937277Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T00:08:28.937277Z"},"graph_snapshot":{"paper":{"title":"Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Gengze Zhou, Jiajun Liu, Jian Zhou, Qi Wu, Sihao Lin, Xunyi Zhao, Zerui Li","submitted_at":"2026-07-28T18:00:34Z","abstract_excerpt":"Autonomous embodied agents must sustain a long decision-making loop that involves perceiving, acting, verifying, and self-correcting over many steps. Current systems sustain this loop through task-specific workflows or embodied policies. We study a third form, agentic embodied control, in which a general-purpose agent holds the loop itself. Using zero-shot navigation as a controlled testbed, we evaluate three software-engineering agent harnesses given only a monocular RGB camera and discrete actions. Under this strictly minimal condition, replicated default-effort configurations reach 70.7$\\pm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26148","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/2607.26148/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":"2607.26148","created_at":"2026-07-30T00:08:28.940953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26148v1","created_at":"2026-07-30T00:08:28.940953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26148","created_at":"2026-07-30T00:08:28.940953+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGCY2RZ2YEPF","created_at":"2026-07-30T00:08:28.940953+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGCY2RZ2YEPFTL5T","created_at":"2026-07-30T00:08:28.940953+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGCY2RZ2","created_at":"2026-07-30T00:08:28.940953+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/RGCY2RZ2YEPFTL5TSE3DPDWSVG","json":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG.json","graph_json":"https://pith.science/api/pith-number/RGCY2RZ2YEPFTL5TSE3DPDWSVG/graph.json","events_json":"https://pith.science/api/pith-number/RGCY2RZ2YEPFTL5TSE3DPDWSVG/events.json","paper":"https://pith.science/paper/RGCY2RZ2"},"agent_actions":{"view_html":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG","download_json":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG.json","view_paper":"https://pith.science/paper/RGCY2RZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26148&json=true","fetch_graph":"https://pith.science/api/pith-number/RGCY2RZ2YEPFTL5TSE3DPDWSVG/graph.json","fetch_events":"https://pith.science/api/pith-number/RGCY2RZ2YEPFTL5TSE3DPDWSVG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG/action/storage_attestation","attest_author":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG/action/author_attestation","sign_citation":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG/action/citation_signature","submit_replication":"https://pith.science/pith/RGCY2RZ2YEPFTL5TSE3DPDWSVG/action/replication_record"}},"created_at":"2026-07-30T00:08:28.940953+00:00","updated_at":"2026-07-30T00:08:28.940953+00:00"}