{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ODBVZKQFQ3WO3JIDZ2AXZZAAWR","short_pith_number":"pith:ODBVZKQF","schema_version":"1.0","canonical_sha256":"70c35caa0586eceda503ce817ce400b463d46aee04dca1e2946ec6a722ad7706","source":{"kind":"arxiv","id":"2409.12959","version":2},"attestation_state":"computed","paper":{"title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Chunyuan Li, Dongzhi Jiang, Guanglu Song, Hongsheng Li, Jiayi Lei, Pan Lu, Peng Gao, Pengshuo Qiu, Renrui Zhang, Yanmin Wu, Yu Liu, Zehui Chen, Ziyu Guo","submitted_at":"2024-09-19T17:59:45Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has paved the way for AI search engines, e.g., SearchGPT, showcasing a new paradigm in human-internet interaction. However, most current AI search engines are limited to text-only settings, neglecting the multimodal user queries and the text-image interleaved nature of website information. Recently, Large Multimodal Models (LMMs) have made impressive strides. Yet, whether they can function as AI search engines remains under-explored, leaving the potential of LMMs in multimodal search an open question. To this end, we first design a delicate pipeline, "},"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":"2409.12959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T17:59:45Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IR"],"title_canon_sha256":"38920445cb82a8bb3759bf929a2381cc67ae16d466d59fbc081acbe64feb8ec6","abstract_canon_sha256":"34b483a336e4f1e19de474cc58364431723c1e859c143d0525399b9d384bc44d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:02.236342Z","signature_b64":"/XIK1Vhi8OVvZGYHnzNMfy8zd79OsWyIQUVDr/aIqUk99E9Ig+zD7Pedr1+qthvIgnoE0zbE2M7dM+oTOiq+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70c35caa0586eceda503ce817ce400b463d46aee04dca1e2946ec6a722ad7706","last_reissued_at":"2026-07-05T09:41:02.235846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:02.235846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMSearch: Benchmarking the Potential of Large Models as Multi-modal Search Engines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IR"],"primary_cat":"cs.CV","authors_text":"Chaoyou Fu, Chunyuan Li, Dongzhi Jiang, Guanglu Song, Hongsheng Li, Jiayi Lei, Pan Lu, Peng Gao, Pengshuo Qiu, Renrui Zhang, Yanmin Wu, Yu Liu, Zehui Chen, Ziyu Guo","submitted_at":"2024-09-19T17:59:45Z","abstract_excerpt":"The advent of Large Language Models (LLMs) has paved the way for AI search engines, e.g., SearchGPT, showcasing a new paradigm in human-internet interaction. However, most current AI search engines are limited to text-only settings, neglecting the multimodal user queries and the text-image interleaved nature of website information. Recently, Large Multimodal Models (LMMs) have made impressive strides. Yet, whether they can function as AI search engines remains under-explored, leaving the potential of LMMs in multimodal search an open question. To this end, we first design a delicate pipeline, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12959","kind":"arxiv","version":2},"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/2409.12959/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":"2409.12959","created_at":"2026-07-05T09:41:02.235902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12959v2","created_at":"2026-07-05T09:41:02.235902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12959","created_at":"2026-07-05T09:41:02.235902+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODBVZKQFQ3WO","created_at":"2026-07-05T09:41:02.235902+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODBVZKQFQ3WO3JID","created_at":"2026-07-05T09:41:02.235902+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODBVZKQF","created_at":"2026-07-05T09:41:02.235902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23881","citing_title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11176","citing_title":"Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05784","citing_title":"TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10832","citing_title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28344","citing_title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28774","citing_title":"Agent Explorative Policy Optimization for Multimodal Agentic Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28774","citing_title":"Agent Explorative Policy Optimization for Multimodal Agentic Reasoning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06943","citing_title":"Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17946","citing_title":"SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13193","citing_title":"FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17946","citing_title":"SVFSearch: A Multimodal Knowledge-Intensive Benchmark for Short-Video Frame Search in the Gaming Vertical Domain","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08980","citing_title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05271","citing_title":"DeepEyesV2: Toward Agentic Multimodal Model","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13193","citing_title":"FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12497","citing_title":"From Web to Pixels: Bringing Agentic Search into Visual Perception","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11864","citing_title":"Very Efficient Listwise Multimodal Reranking for Long Documents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10832","citing_title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07177","citing_title":"HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26752","citing_title":"GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01278","citing_title":"Valley3: Scaling Omni Foundation Models for E-commerce","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR","json":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR.json","graph_json":"https://pith.science/api/pith-number/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/graph.json","events_json":"https://pith.science/api/pith-number/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/events.json","paper":"https://pith.science/paper/ODBVZKQF"},"agent_actions":{"view_html":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR","download_json":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR.json","view_paper":"https://pith.science/paper/ODBVZKQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12959&json=true","fetch_graph":"https://pith.science/api/pith-number/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/graph.json","fetch_events":"https://pith.science/api/pith-number/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/action/storage_attestation","attest_author":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/action/author_attestation","sign_citation":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/action/citation_signature","submit_replication":"https://pith.science/pith/ODBVZKQFQ3WO3JIDZ2AXZZAAWR/action/replication_record"}},"created_at":"2026-07-05T09:41:02.235902+00:00","updated_at":"2026-07-05T09:41:02.235902+00:00"}