{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L7F2WMTQEJ4YWIWGPY7LKTXWQJ","short_pith_number":"pith:L7F2WMTQ","schema_version":"1.0","canonical_sha256":"5fcbab327022798b22c67e3eb54ef6827b4951114511f200135d9ee00e1712fe","source":{"kind":"arxiv","id":"2501.11858","version":2},"attestation_state":"computed","paper":{"title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiahao Li, Jinyi Hu, Lei Shi, Maosong Sun, Ran Li, Shengding Hu, Shiqi Dai, Tianyu Yu, Weize Chen, Yang Shi, Yuge Tu, Zhili Cheng","submitted_at":"2025-01-21T03:22:10Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown significant advancements, providing a promising future for embodied agents. Existing benchmarks for evaluating MLLMs primarily utilize static images or videos, limiting assessments to non-interactive scenarios. Meanwhile, existing embodied AI benchmarks are task-specific and not diverse enough, which do not adequately evaluate the embodied capabilities of MLLMs. To address this, we propose EmbodiedEval, a comprehensive and interactive evaluation benchmark for MLLMs with embodied tasks. EmbodiedEval features 328 distinct tasks within 125 varie"},"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":"2501.11858","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-21T03:22:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6f9e969d7ac5dfadb096d739ce60d871b46b1af9ef957d9a01d8776750261aab","abstract_canon_sha256":"c25ab8124e368174a55ca7888ed8ef9c4d0dc3633a28529e4e99d0b9f14ab1bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:35.483510Z","signature_b64":"REWVgSkzP/45shQ1FBoL3D8jdqv5bhZp+8+TezIz8I+XOl+E0FMoKnxzzp5NTPwG9BtkgQHzv2HkZyfXdQ4eCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fcbab327022798b22c67e3eb54ef6827b4951114511f200135d9ee00e1712fe","last_reissued_at":"2026-07-05T10:47:35.483043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:35.483043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiahao Li, Jinyi Hu, Lei Shi, Maosong Sun, Ran Li, Shengding Hu, Shiqi Dai, Tianyu Yu, Weize Chen, Yang Shi, Yuge Tu, Zhili Cheng","submitted_at":"2025-01-21T03:22:10Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown significant advancements, providing a promising future for embodied agents. Existing benchmarks for evaluating MLLMs primarily utilize static images or videos, limiting assessments to non-interactive scenarios. Meanwhile, existing embodied AI benchmarks are task-specific and not diverse enough, which do not adequately evaluate the embodied capabilities of MLLMs. To address this, we propose EmbodiedEval, a comprehensive and interactive evaluation benchmark for MLLMs with embodied tasks. EmbodiedEval features 328 distinct tasks within 125 varie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11858","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/2501.11858/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":"2501.11858","created_at":"2026-07-05T10:47:35.483097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11858v2","created_at":"2026-07-05T10:47:35.483097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11858","created_at":"2026-07-05T10:47:35.483097+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7F2WMTQEJ4Y","created_at":"2026-07-05T10:47:35.483097+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7F2WMTQEJ4YWIWG","created_at":"2026-07-05T10:47:35.483097+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7F2WMTQ","created_at":"2026-07-05T10:47:35.483097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12207","citing_title":"Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10366","citing_title":"A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09669","citing_title":"SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24893","citing_title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23187","citing_title":"IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18746","citing_title":"ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18984","citing_title":"Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos","ref_index":6,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23511","citing_title":"Breaking the Secret: Economic Interventions for Combating Collusion in Embodied Multi-Agent Systems","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13633","citing_title":"ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14785","citing_title":"MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ","json":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ.json","graph_json":"https://pith.science/api/pith-number/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/graph.json","events_json":"https://pith.science/api/pith-number/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/events.json","paper":"https://pith.science/paper/L7F2WMTQ"},"agent_actions":{"view_html":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ","download_json":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ.json","view_paper":"https://pith.science/paper/L7F2WMTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11858&json=true","fetch_graph":"https://pith.science/api/pith-number/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/action/storage_attestation","attest_author":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/action/author_attestation","sign_citation":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/action/citation_signature","submit_replication":"https://pith.science/pith/L7F2WMTQEJ4YWIWGPY7LKTXWQJ/action/replication_record"}},"created_at":"2026-07-05T10:47:35.483097+00:00","updated_at":"2026-07-05T10:47:35.483097+00:00"}