{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ASW5BTKQXEVM44OJ4RNY3ZDIYS","short_pith_number":"pith:ASW5BTKQ","schema_version":"1.0","canonical_sha256":"04add0cd50b92ace71c9e45b8de468c4b9a4c0a0b270e45e020b801bfc4ca538","source":{"kind":"arxiv","id":"2607.11106","version":1},"attestation_state":"computed","paper":{"title":"Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Hanhui Li, Jianhua Han, Kun Xiang, Mingyang Zhang, Quanlin Chen, Wentao Hu, Xiaodan Liang, Xiuwei Chen, Zehua Ma, Zisheng Chen","submitted_at":"2026-07-13T05:32:00Z","abstract_excerpt":"Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the \"Thinking with Images\" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the train"},"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":"2607.11106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-13T05:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"df8a0fc0589897f3fc77fdb95d324753e035a79bbdfaa780f57deb2ff3b77c2f","abstract_canon_sha256":"b9ff64c4aa9f58a417d05099763e5f00df9e7a0abeca8dd86e8c1f867acd35c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:16.735114Z","signature_b64":"Eg2RQC0FM8kyA0cAUGpr4VMStTJQvmUyA2IjGcoWAQE36CEsL2613vHjR/D/SvYMub1kNa0HEE55Z1bX49JpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04add0cd50b92ace71c9e45b8de468c4b9a4c0a0b270e45e020b801bfc4ca538","last_reissued_at":"2026-07-14T01:22:16.734221Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:16.734221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Hanhui Li, Jianhua Han, Kun Xiang, Mingyang Zhang, Quanlin Chen, Wentao Hu, Xiaodan Liang, Xiuwei Chen, Zehua Ma, Zisheng Chen","submitted_at":"2026-07-13T05:32:00Z","abstract_excerpt":"Recent multimodal large language models (MLLMs) have made remarkable progress on fine-grained perception tasks under the \"Thinking with Images\" (TwI) paradigm by iteratively performing various visual tool operations. However, this paradigm relies heavily on frequent external tool calls and repeated image re-encoding, which leads to substantial computational overhead and inference latency. To address these issues, we propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability. BEE directly incorporates visual tool invocation behaviors into the train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11106","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/2607.11106/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":"2607.11106","created_at":"2026-07-14T01:22:16.734682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11106v1","created_at":"2026-07-14T01:22:16.734682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11106","created_at":"2026-07-14T01:22:16.734682+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASW5BTKQXEVM","created_at":"2026-07-14T01:22:16.734682+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASW5BTKQXEVM44OJ","created_at":"2026-07-14T01:22:16.734682+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASW5BTKQ","created_at":"2026-07-14T01:22:16.734682+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/ASW5BTKQXEVM44OJ4RNY3ZDIYS","json":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS.json","graph_json":"https://pith.science/api/pith-number/ASW5BTKQXEVM44OJ4RNY3ZDIYS/graph.json","events_json":"https://pith.science/api/pith-number/ASW5BTKQXEVM44OJ4RNY3ZDIYS/events.json","paper":"https://pith.science/paper/ASW5BTKQ"},"agent_actions":{"view_html":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS","download_json":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS.json","view_paper":"https://pith.science/paper/ASW5BTKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11106&json=true","fetch_graph":"https://pith.science/api/pith-number/ASW5BTKQXEVM44OJ4RNY3ZDIYS/graph.json","fetch_events":"https://pith.science/api/pith-number/ASW5BTKQXEVM44OJ4RNY3ZDIYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS/action/storage_attestation","attest_author":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS/action/author_attestation","sign_citation":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS/action/citation_signature","submit_replication":"https://pith.science/pith/ASW5BTKQXEVM44OJ4RNY3ZDIYS/action/replication_record"}},"created_at":"2026-07-14T01:22:16.734682+00:00","updated_at":"2026-07-14T01:22:16.734682+00:00"}