{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MB6WHGETVQFP756JN6QQIRPP76","short_pith_number":"pith:MB6WHGET","schema_version":"1.0","canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","source":{"kind":"arxiv","id":"2408.06327","version":1},"attestation_state":"computed","paper":{"title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aohan Zeng, Chan Hee Song, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Hao Yu, Iat Long Iong, Jiadai Sun, Jie Tang, Lihang Pan, Ming Ding, Qinkai Zheng, Shudan Zhang, Shuntian Yao, Siyi Cheng, Tianjie Zhang, Wenyi Hong, Xiao Liu, Xiaotao Gu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xueqiao Sun, Yifan Xu, Yu Gu, Yu Su, Yuxiao Dong, Yu Yang, Zehan Qi, Zhengxiao Du","submitted_at":"2024-08-12T17:44:17Z","abstract_excerpt":"Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual fou"},"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":"2408.06327","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-12T17:44:17Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"ae8ef57dbf112370835b7d2939117ef5796c9de295a8a0e177525721e8bfb0a9","abstract_canon_sha256":"1da290cab9d0f62ac82f58a318eba145ba520c661970f32b1659aca69eaa1fef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:39.208241Z","signature_b64":"A0iZd3vwnUchU/WgMvyARtW8TCtUe7NqRTmXV/xDivYyKo9xBWCOWr4ZTFmXiYAorsKjt3xsERWdMTeknqK3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"607d639893ac0afff7c96fa10445efffbe4ceeb2846d4de25ccad73d9ce31aff","last_reissued_at":"2026-07-05T08:54:39.207756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:39.207756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Aohan Zeng, Chan Hee Song, Hanchen Zhang, Hanlin Zhao, Hanyu Lai, Hao Yu, Iat Long Iong, Jiadai Sun, Jie Tang, Lihang Pan, Ming Ding, Qinkai Zheng, Shudan Zhang, Shuntian Yao, Siyi Cheng, Tianjie Zhang, Wenyi Hong, Xiao Liu, Xiaotao Gu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xueqiao Sun, Yifan Xu, Yu Gu, Yu Su, Yuxiao Dong, Yu Yang, Zehan Qi, Zhengxiao Du","submitted_at":"2024-08-12T17:44:17Z","abstract_excerpt":"Large Multimodal Models (LMMs) have ushered in a new era in artificial intelligence, merging capabilities in both language and vision to form highly capable Visual Foundation Agents. These agents are postulated to excel across a myriad of tasks, potentially approaching general artificial intelligence. However, existing benchmarks fail to sufficiently challenge or showcase the full potential of LMMs in complex, real-world environments. To address this gap, we introduce VisualAgentBench (VAB), a comprehensive and pioneering benchmark specifically designed to train and evaluate LMMs as visual fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06327","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/2408.06327/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":"2408.06327","created_at":"2026-07-05T08:54:39.207815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06327v1","created_at":"2026-07-05T08:54:39.207815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06327","created_at":"2026-07-05T08:54:39.207815+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB6WHGETVQFP","created_at":"2026-07-05T08:54:39.207815+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB6WHGETVQFP756J","created_at":"2026-07-05T08:54:39.207815+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB6WHGET","created_at":"2026-07-05T08:54:39.207815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06118","citing_title":"WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10366","citing_title":"A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31392","citing_title":"ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26396","citing_title":"Advancing Creative Physical Intelligence in Large Multimodal Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21460","citing_title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16909","citing_title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12501","citing_title":"Covering Human Action Space for Computer Use: Data Synthesis and Benchmark","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04097","citing_title":"CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08703","citing_title":"QoS-QoE Translation with Large Language Model","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76","json":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76.json","graph_json":"https://pith.science/api/pith-number/MB6WHGETVQFP756JN6QQIRPP76/graph.json","events_json":"https://pith.science/api/pith-number/MB6WHGETVQFP756JN6QQIRPP76/events.json","paper":"https://pith.science/paper/MB6WHGET"},"agent_actions":{"view_html":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76","download_json":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76.json","view_paper":"https://pith.science/paper/MB6WHGET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06327&json=true","fetch_graph":"https://pith.science/api/pith-number/MB6WHGETVQFP756JN6QQIRPP76/graph.json","fetch_events":"https://pith.science/api/pith-number/MB6WHGETVQFP756JN6QQIRPP76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/action/storage_attestation","attest_author":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/action/author_attestation","sign_citation":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/action/citation_signature","submit_replication":"https://pith.science/pith/MB6WHGETVQFP756JN6QQIRPP76/action/replication_record"}},"created_at":"2026-07-05T08:54:39.207815+00:00","updated_at":"2026-07-05T08:54:39.207815+00:00"}