{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MLAZVDUY7ZXW2ETLXGTZQZKAUN","short_pith_number":"pith:MLAZVDUY","schema_version":"1.0","canonical_sha256":"62c19a8e98fe6f6d126bb9a7986540a366025a1c384409f39a117e567ccd32fd","source":{"kind":"arxiv","id":"2506.08691","version":1},"attestation_state":"computed","paper":{"title":"VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congzhi Zhang, Fei Ma, Haowen Sun, Heng Chang, Jiawei Peng, Weijiang Yu, Yilong Lai, Zhenglin Wang","submitted_at":"2025-06-10T11:02:36Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this paper, we propose VReST, a novel training-free approach that enhances Reasoning in LVLMs through Monte Carlo Tree Search and Self-Reward mechanisms. VReST meticulously traverses the reasoning landscape by establishing a search tree, where each node encapsulates a reasoning step, and each path delineates a comprehensive reasoning sequence. Our innovative mult"},"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":"2506.08691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T11:02:36Z","cross_cats_sorted":[],"title_canon_sha256":"72ac99ec357bff474afa8f00ff52ee25594a7684d16938585d981e0ea2ceb8d8","abstract_canon_sha256":"f6bcbb6b7705e886624a1827ce24c7c28fd4cffaf743c1307faf75f9ea73c8fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:11.943499Z","signature_b64":"DVIp3a+Gauq+L2YWAaps6ZmKfFtFx1HE0f+/WOS4tX08VfHZoILa7L/RxGbHQMqIVlr7QOGuRBUlDuhnXTPnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c19a8e98fe6f6d126bb9a7986540a366025a1c384409f39a117e567ccd32fd","last_reissued_at":"2026-07-05T11:19:11.943000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:11.943000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congzhi Zhang, Fei Ma, Haowen Sun, Heng Chang, Jiawei Peng, Weijiang Yu, Yilong Lai, Zhenglin Wang","submitted_at":"2025-06-10T11:02:36Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is still constrained, especially when employing Chain-of-Thought prompting techniques. In this paper, we propose VReST, a novel training-free approach that enhances Reasoning in LVLMs through Monte Carlo Tree Search and Self-Reward mechanisms. VReST meticulously traverses the reasoning landscape by establishing a search tree, where each node encapsulates a reasoning step, and each path delineates a comprehensive reasoning sequence. Our innovative mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08691","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/2506.08691/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":"2506.08691","created_at":"2026-07-05T11:19:11.943059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08691v1","created_at":"2026-07-05T11:19:11.943059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08691","created_at":"2026-07-05T11:19:11.943059+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLAZVDUY7ZXW","created_at":"2026-07-05T11:19:11.943059+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLAZVDUY7ZXW2ETL","created_at":"2026-07-05T11:19:11.943059+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLAZVDUY","created_at":"2026-07-05T11:19:11.943059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN","json":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN.json","graph_json":"https://pith.science/api/pith-number/MLAZVDUY7ZXW2ETLXGTZQZKAUN/graph.json","events_json":"https://pith.science/api/pith-number/MLAZVDUY7ZXW2ETLXGTZQZKAUN/events.json","paper":"https://pith.science/paper/MLAZVDUY"},"agent_actions":{"view_html":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN","download_json":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN.json","view_paper":"https://pith.science/paper/MLAZVDUY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08691&json=true","fetch_graph":"https://pith.science/api/pith-number/MLAZVDUY7ZXW2ETLXGTZQZKAUN/graph.json","fetch_events":"https://pith.science/api/pith-number/MLAZVDUY7ZXW2ETLXGTZQZKAUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN/action/storage_attestation","attest_author":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN/action/author_attestation","sign_citation":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN/action/citation_signature","submit_replication":"https://pith.science/pith/MLAZVDUY7ZXW2ETLXGTZQZKAUN/action/replication_record"}},"created_at":"2026-07-05T11:19:11.943059+00:00","updated_at":"2026-07-05T11:19:11.943059+00:00"}