{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FP7KC53RJ4SWWRIGNT7YKNSQS","short_pith_number":"pith:3FP7KC53","schema_version":"1.0","canonical_sha256":"d95ff50bbb8a792b5a283367fc29b2849678b7493dbe0d1af9d0d738db678af2","source":{"kind":"arxiv","id":"2603.22169","version":2},"attestation_state":"computed","paper":{"title":"Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Artem Trandofilov, Daniia Zinniatullina, Dmitrii Maliukov, Dmitrii Plotnikov, Dmitrij Kosenkov, Dzmitry Tsetserukou, Georgii Gazaryan, Iaroslav Kolomiets, Kirill Bogatikov, Miguel Altamirano Cabrera, Mikhail Konenkov, Timofei Kozlov","submitted_at":"2026-03-23T16:28:36Z","abstract_excerpt":"We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment. In our framework, executable Behavior Trees are repeatedly refined by a Large Language Model actor using structured natural-language feedback produced by a Vision-Language Model critic that observes the physical robot and execution traces. Unlike conventional reinforcement learning, policy u"},"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":"2603.22169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-23T16:28:36Z","cross_cats_sorted":[],"title_canon_sha256":"926330fe307f16fc22983a0673606fd9c21be72b69b8195afd1b849a61aaca3b","abstract_canon_sha256":"af7518854d2c84f51ecd9b1a15df6948493053d2dd12297dd62c2857864d5729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:22.948432Z","signature_b64":"3I15y+S2MWHemPNkEFHOQta/kQTxgCrIq6Ik5AncIfkd9OJTJeQjzF+e8mIqJX5LcqBK8E96dCDlrSXe9f+nAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d95ff50bbb8a792b5a283367fc29b2849678b7493dbe0d1af9d0d738db678af2","last_reissued_at":"2026-06-23T02:13:22.948001Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:22.948001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Closed-Loop Verbal Reinforcement Learning for Task-Level Robotic Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Artem Trandofilov, Daniia Zinniatullina, Dmitrii Maliukov, Dmitrii Plotnikov, Dmitrij Kosenkov, Dzmitry Tsetserukou, Georgii Gazaryan, Iaroslav Kolomiets, Kirill Bogatikov, Miguel Altamirano Cabrera, Mikhail Konenkov, Timofei Kozlov","submitted_at":"2026-03-23T16:28:36Z","abstract_excerpt":"We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative policy improvement through interaction with the physical environment. In our framework, executable Behavior Trees are repeatedly refined by a Large Language Model actor using structured natural-language feedback produced by a Vision-Language Model critic that observes the physical robot and execution traces. Unlike conventional reinforcement learning, policy u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.22169","kind":"arxiv","version":2},"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/2603.22169/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":"2603.22169","created_at":"2026-06-23T02:13:22.948058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.22169v2","created_at":"2026-06-23T02:13:22.948058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.22169","created_at":"2026-06-23T02:13:22.948058+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FP7KC53RJ4S","created_at":"2026-06-23T02:13:22.948058+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FP7KC53RJ4SWWRI","created_at":"2026-06-23T02:13:22.948058+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FP7KC53","created_at":"2026-06-23T02:13:22.948058+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/3FP7KC53RJ4SWWRIGNT7YKNSQS","json":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS.json","graph_json":"https://pith.science/api/pith-number/3FP7KC53RJ4SWWRIGNT7YKNSQS/graph.json","events_json":"https://pith.science/api/pith-number/3FP7KC53RJ4SWWRIGNT7YKNSQS/events.json","paper":"https://pith.science/paper/3FP7KC53"},"agent_actions":{"view_html":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS","download_json":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS.json","view_paper":"https://pith.science/paper/3FP7KC53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.22169&json=true","fetch_graph":"https://pith.science/api/pith-number/3FP7KC53RJ4SWWRIGNT7YKNSQS/graph.json","fetch_events":"https://pith.science/api/pith-number/3FP7KC53RJ4SWWRIGNT7YKNSQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS/action/storage_attestation","attest_author":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS/action/author_attestation","sign_citation":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS/action/citation_signature","submit_replication":"https://pith.science/pith/3FP7KC53RJ4SWWRIGNT7YKNSQS/action/replication_record"}},"created_at":"2026-06-23T02:13:22.948058+00:00","updated_at":"2026-06-23T02:13:22.948058+00:00"}