{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5B6DVBEDZR2FK4P6RRBHHI2NX","short_pith_number":"pith:O5B6DVBE","schema_version":"1.0","canonical_sha256":"7743e1d4241e63a2ab8ff462139d1a6dd1fe7e15d7191a6e7072d5d8ca852c43","source":{"kind":"arxiv","id":"2508.08816","version":1},"attestation_state":"computed","paper":{"title":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dan Meng, Haonan Lu, Jun Yang, Xudong Zhang, Yuechen Wang, Yuming Qiao, Zhenyu Yang","submitted_at":"2025-08-12T10:17:12Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (mRAG) has emerged as a promising solution to address the temporal limitations of Multimodal Large Language Models (MLLMs) in real-world scenarios like news analysis and trending topics. However, existing approaches often suffer from rigid retrieval strategies and under-utilization of visual information. To bridge this gap, we propose E-Agent, an agent framework featuring two key innovations: a mRAG planner trained to dynamically orchestrate multimodal tools based on contextual reasoning, and a task executor employing tool-aware execution sequencing to"},"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":"2508.08816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-12T10:17:12Z","cross_cats_sorted":[],"title_canon_sha256":"f33b4be96b9b3a7622e7a9f294d8e0b4ff258674847ed95206459df0e3a1d5f5","abstract_canon_sha256":"47d7c51f97ea7f180a125d3d3a5263261341af5fcf151d8e9d5e272ea58cd1b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:34.748367Z","signature_b64":"YYxEXN/jdHDhbuLp6se5KmD1AgTF++DOKjaHLaI82ZWNwpvg1YhjNwEN7+uyPKnh6hOTExfV9f1vxFVXEcjlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7743e1d4241e63a2ab8ff462139d1a6dd1fe7e15d7191a6e7072d5d8ca852c43","last_reissued_at":"2026-07-05T11:52:34.747872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:34.747872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Agent: Optimizing Planning Capability for Multimodal Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dan Meng, Haonan Lu, Jun Yang, Xudong Zhang, Yuechen Wang, Yuming Qiao, Zhenyu Yang","submitted_at":"2025-08-12T10:17:12Z","abstract_excerpt":"Multimodal Retrieval-Augmented Generation (mRAG) has emerged as a promising solution to address the temporal limitations of Multimodal Large Language Models (MLLMs) in real-world scenarios like news analysis and trending topics. However, existing approaches often suffer from rigid retrieval strategies and under-utilization of visual information. To bridge this gap, we propose E-Agent, an agent framework featuring two key innovations: a mRAG planner trained to dynamically orchestrate multimodal tools based on contextual reasoning, and a task executor employing tool-aware execution sequencing to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08816","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/2508.08816/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":"2508.08816","created_at":"2026-07-05T11:52:34.747934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08816v1","created_at":"2026-07-05T11:52:34.747934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08816","created_at":"2026-07-05T11:52:34.747934+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5B6DVBEDZR2","created_at":"2026-07-05T11:52:34.747934+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5B6DVBEDZR2FK4P","created_at":"2026-07-05T11:52:34.747934+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5B6DVBE","created_at":"2026-07-05T11:52:34.747934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05967","citing_title":"M$^3$Prune: Hierarchical Collaborative Pruning for Efficient Multi-Modal Multi-Agent Retrieval-Augmented Generation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX","json":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX.json","graph_json":"https://pith.science/api/pith-number/O5B6DVBEDZR2FK4P6RRBHHI2NX/graph.json","events_json":"https://pith.science/api/pith-number/O5B6DVBEDZR2FK4P6RRBHHI2NX/events.json","paper":"https://pith.science/paper/O5B6DVBE"},"agent_actions":{"view_html":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX","download_json":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX.json","view_paper":"https://pith.science/paper/O5B6DVBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08816&json=true","fetch_graph":"https://pith.science/api/pith-number/O5B6DVBEDZR2FK4P6RRBHHI2NX/graph.json","fetch_events":"https://pith.science/api/pith-number/O5B6DVBEDZR2FK4P6RRBHHI2NX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX/action/storage_attestation","attest_author":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX/action/author_attestation","sign_citation":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX/action/citation_signature","submit_replication":"https://pith.science/pith/O5B6DVBEDZR2FK4P6RRBHHI2NX/action/replication_record"}},"created_at":"2026-07-05T11:52:34.747934+00:00","updated_at":"2026-07-05T11:52:34.747934+00:00"}