{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:K6XZZLPBHH7XA7BVF3EA4VQ7QL","short_pith_number":"pith:K6XZZLPB","schema_version":"1.0","canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","source":{"kind":"arxiv","id":"2608.02217","version":1},"attestation_state":"computed","paper":{"title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Deng, Jiashen Hua, Jieping Ye, Yizheng Wu","submitted_at":"2026-08-03T13:38:37Z","abstract_excerpt":"Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool interactions. Effective visual tool use requires three capabilities: grounding tool calls in visual context, composing tools across multiple steps, and adapting reasoning to tool-returned observations. However, existing approaches largely focus on grounding within fixed tool spaces and rigid invocation patterns, leaving composition and adaptation insufficiently addressed. We present VC-Tooler, which learns visual tool use as a compositional and ad"},"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":"2608.02217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T13:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"936b6f85d3ca84a953a79c20348dc3fb93757dbdf5c8d510e6023d31a8cd7814","abstract_canon_sha256":"50df5b4724c403606fe2bf472622915d3c81d0f6508667a4267de9483c351a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:25.695729Z","signature_b64":"cMNXeKzOipCX2uPmz8yY0wloLtmKhJtC3XarUfz8sIcDJl3a+WyZio0UlKDYokj5X7LLnMwKbOINaHCbz/Q1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57af9cade139ff707c352ec80e561f82f08ffffc498d251e9e733c9ab029a7e4","last_reissued_at":"2026-08-04T02:11:25.694179Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:25.694179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VC-Tooler: Learning Compositional and Adaptive Visual Tool Use","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Deng, Jiashen Hua, Jieping Ye, Yizheng Wu","submitted_at":"2026-08-03T13:38:37Z","abstract_excerpt":"Agentic multimodal reasoning extends passive image understanding by allowing VLMs to actively acquire and refine visual evidence through visual tool interactions. Effective visual tool use requires three capabilities: grounding tool calls in visual context, composing tools across multiple steps, and adapting reasoning to tool-returned observations. However, existing approaches largely focus on grounding within fixed tool spaces and rigid invocation patterns, leaving composition and adaptation insufficiently addressed. We present VC-Tooler, which learns visual tool use as a compositional and ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02217","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/2608.02217/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":"2608.02217","created_at":"2026-08-04T02:11:25.695727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02217v1","created_at":"2026-08-04T02:11:25.695727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02217","created_at":"2026-08-04T02:11:25.695727+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6XZZLPBHH7X","created_at":"2026-08-04T02:11:25.695727+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6XZZLPBHH7XA7BV","created_at":"2026-08-04T02:11:25.695727+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6XZZLPB","created_at":"2026-08-04T02:11:25.695727+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/K6XZZLPBHH7XA7BVF3EA4VQ7QL","json":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL.json","graph_json":"https://pith.science/api/pith-number/K6XZZLPBHH7XA7BVF3EA4VQ7QL/graph.json","events_json":"https://pith.science/api/pith-number/K6XZZLPBHH7XA7BVF3EA4VQ7QL/events.json","paper":"https://pith.science/paper/K6XZZLPB"},"agent_actions":{"view_html":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL","download_json":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL.json","view_paper":"https://pith.science/paper/K6XZZLPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02217&json=true","fetch_graph":"https://pith.science/api/pith-number/K6XZZLPBHH7XA7BVF3EA4VQ7QL/graph.json","fetch_events":"https://pith.science/api/pith-number/K6XZZLPBHH7XA7BVF3EA4VQ7QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/action/storage_attestation","attest_author":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/action/author_attestation","sign_citation":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/action/citation_signature","submit_replication":"https://pith.science/pith/K6XZZLPBHH7XA7BVF3EA4VQ7QL/action/replication_record"}},"created_at":"2026-08-04T02:11:25.695727+00:00","updated_at":"2026-08-04T02:11:25.695727+00:00"}