{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HGPLKCGFMDDUEFHKFVUUNJWGXZ","short_pith_number":"pith:HGPLKCGF","schema_version":"1.0","canonical_sha256":"399eb508c560c74214ea2d6946a6c6be474d93e4e1d51a0c9dc16fdcb8b03cb1","source":{"kind":"arxiv","id":"2605.21605","version":1},"attestation_state":"computed","paper":{"title":"GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuxiang Zhai, Jialin Gao, Jianyu Lai, Lei Zhu, Sixiang Chen, Tian Ye, Xinyu Geng, Xuanhua He, Yunlong Lin, Zhaohu Xing","submitted_at":"2026-05-20T18:12:29Z","abstract_excerpt":"Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and demanding, we aim to develop a general image-generation agent that can self-evolve through trajectories and use tools more effectively across varied generation challenges. To this end, we propose GenEvolve, a self-evolving framework based on Tool-Orchestrated Visual Experience Distillation. In GenEvolve, each generation attempt is modeled as a tool-orchestrated tra"},"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":"2605.21605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T18:12:29Z","cross_cats_sorted":[],"title_canon_sha256":"ec35b30a90d96c4b1a23e447dc76ba92d8dcb9e4abf9d14b29f07c4a1b6ae454","abstract_canon_sha256":"2f7656811dff7e8fa89f8d5af2aabca03acbc0d06fc7880799a6dcf98558a694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:25.088770Z","signature_b64":"GEjVEleigVIuFoxIGAIbdTdVFqc2aIWH9xRhANtSNHel+iPzQyZOIDQ13Mbf0zCDX6IcA+wSgPB9T1mPM+2JBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"399eb508c560c74214ea2d6946a6c6be474d93e4e1d51a0c9dc16fdcb8b03cb1","last_reissued_at":"2026-05-22T01:03:25.088006Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:25.088006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fuxiang Zhai, Jialin Gao, Jianyu Lai, Lei Zhu, Sixiang Chen, Tian Ye, Xinyu Geng, Xuanhua He, Yunlong Lin, Zhaohu Xing","submitted_at":"2026-05-20T18:12:29Z","abstract_excerpt":"Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and demanding, we aim to develop a general image-generation agent that can self-evolve through trajectories and use tools more effectively across varied generation challenges. To this end, we propose GenEvolve, a self-evolving framework based on Tool-Orchestrated Visual Experience Distillation. In GenEvolve, each generation attempt is modeled as a tool-orchestrated tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21605","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/2605.21605/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":"2605.21605","created_at":"2026-05-22T01:03:25.088133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21605v1","created_at":"2026-05-22T01:03:25.088133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21605","created_at":"2026-05-22T01:03:25.088133+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGPLKCGFMDDU","created_at":"2026-05-22T01:03:25.088133+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGPLKCGFMDDUEFHK","created_at":"2026-05-22T01:03:25.088133+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGPLKCGF","created_at":"2026-05-22T01:03:25.088133+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/HGPLKCGFMDDUEFHKFVUUNJWGXZ","json":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ.json","graph_json":"https://pith.science/api/pith-number/HGPLKCGFMDDUEFHKFVUUNJWGXZ/graph.json","events_json":"https://pith.science/api/pith-number/HGPLKCGFMDDUEFHKFVUUNJWGXZ/events.json","paper":"https://pith.science/paper/HGPLKCGF"},"agent_actions":{"view_html":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ","download_json":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ.json","view_paper":"https://pith.science/paper/HGPLKCGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21605&json=true","fetch_graph":"https://pith.science/api/pith-number/HGPLKCGFMDDUEFHKFVUUNJWGXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HGPLKCGFMDDUEFHKFVUUNJWGXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ/action/storage_attestation","attest_author":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ/action/author_attestation","sign_citation":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ/action/citation_signature","submit_replication":"https://pith.science/pith/HGPLKCGFMDDUEFHKFVUUNJWGXZ/action/replication_record"}},"created_at":"2026-05-22T01:03:25.088133+00:00","updated_at":"2026-05-22T01:03:25.088133+00:00"}