{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HTCFIL6HZCJRPR4E7JZKTBLJ2I","short_pith_number":"pith:HTCFIL6H","schema_version":"1.0","canonical_sha256":"3cc4542fc7c89317c784fa72a98569d21c130bea8af498d36afafc4e2a4de335","source":{"kind":"arxiv","id":"2606.30185","version":1},"attestation_state":"computed","paper":{"title":"Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dexin Wang, Guanjun Jiang, Hao-Xuan Ma, Lei Lv, Li Xu, Mengyu Zhou, Mingshuai Chen, Tiancheng Zhao, Xiaoxi Jiang, Yanting Miao, Yutao Sun","submitted_at":"2026-06-29T11:59:01Z","abstract_excerpt":"Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates. On a small labeled training subset, the agent inspects its own correct and incorrect attempts and evolves two complementary capabilities: reusable reasoning skills for cognitive bottlenecks, and executable visual tools for perceptual ones. Each generated tool is paired with a skill that specifies when to invoke it, and both capability types accumulate in a persistent librar"},"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":"2606.30185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T11:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"0fe209dcc44ffb0bedbd9a5ada30090dbdff9b121989c013fcd4cbde3aa32384","abstract_canon_sha256":"a0e315ff0b21ecac3e47d4ab5b42dd8937c8601fa2a971d1a54ffda88bb4cb53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:52.959873Z","signature_b64":"A81NDRv0tvwDtohcYhedvCMIttBtT/9/yia2DOQyURNKs0jCrGzhbZCUV4gH7XWPjIWn7lWUS4LH1GsgJzJ2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cc4542fc7c89317c784fa72a98569d21c130bea8af498d36afafc4e2a4de335","last_reissued_at":"2026-06-30T02:17:52.959069Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:52.959069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamo: Dynamic Skill-Tool Evolution for Vision-Language Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dexin Wang, Guanjun Jiang, Hao-Xuan Ma, Lei Lv, Li Xu, Mengyu Zhou, Mingshuai Chen, Tiancheng Zhao, Xiaoxi Jiang, Yanting Miao, Yutao Sun","submitted_at":"2026-06-29T11:59:01Z","abstract_excerpt":"Improving vision-language models (VLMs) on visual reasoning typically requires retraining or hand-designed prompts and tools. We present Dynamo, a training-free framework that adapts a frozen VLM without any weight updates. On a small labeled training subset, the agent inspects its own correct and incorrect attempts and evolves two complementary capabilities: reusable reasoning skills for cognitive bottlenecks, and executable visual tools for perceptual ones. Each generated tool is paired with a skill that specifies when to invoke it, and both capability types accumulate in a persistent librar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30185","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/2606.30185/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":"2606.30185","created_at":"2026-06-30T02:17:52.959172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30185v1","created_at":"2026-06-30T02:17:52.959172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30185","created_at":"2026-06-30T02:17:52.959172+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTCFIL6HZCJR","created_at":"2026-06-30T02:17:52.959172+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTCFIL6HZCJRPR4E","created_at":"2026-06-30T02:17:52.959172+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTCFIL6H","created_at":"2026-06-30T02:17:52.959172+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/HTCFIL6HZCJRPR4E7JZKTBLJ2I","json":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I.json","graph_json":"https://pith.science/api/pith-number/HTCFIL6HZCJRPR4E7JZKTBLJ2I/graph.json","events_json":"https://pith.science/api/pith-number/HTCFIL6HZCJRPR4E7JZKTBLJ2I/events.json","paper":"https://pith.science/paper/HTCFIL6H"},"agent_actions":{"view_html":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I","download_json":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I.json","view_paper":"https://pith.science/paper/HTCFIL6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30185&json=true","fetch_graph":"https://pith.science/api/pith-number/HTCFIL6HZCJRPR4E7JZKTBLJ2I/graph.json","fetch_events":"https://pith.science/api/pith-number/HTCFIL6HZCJRPR4E7JZKTBLJ2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I/action/storage_attestation","attest_author":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I/action/author_attestation","sign_citation":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I/action/citation_signature","submit_replication":"https://pith.science/pith/HTCFIL6HZCJRPR4E7JZKTBLJ2I/action/replication_record"}},"created_at":"2026-06-30T02:17:52.959172+00:00","updated_at":"2026-06-30T02:17:52.959172+00:00"}