{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHQVCX474M63G67R7LUOLOWFX2","short_pith_number":"pith:HHQVCX47","schema_version":"1.0","canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","source":{"kind":"arxiv","id":"2502.09560","version":3},"attestation_state":"computed","paper":{"title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation.","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cheng Qian, Hanyang Chen, Heng Ji, Huan Zhang, Junyu Zhang, Kangrui Wang, Manling Li, Mark Zhao, Marziyeh Movahedi, Qineng Wang, Rui Yang, Teja Venkat Koripella, Tong Zhang","submitted_at":"2025-02-13T18:11:34Z","abstract_excerpt":"Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1,128 testing tasks across four environments, ranging from high-level semantic tasks (e.g., household) to low-level "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2502.09560","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T18:11:34Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"f197cab08bcf541567652650012478e17043804ab59a7cb2839f5e4a50c9323a","abstract_canon_sha256":"12cbdefdd1c0e9a1766ce06a931d3e50de0b2822ea302800d0d69603632a1381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.119250Z","signature_b64":"h6LkOdGVDzsGVTkwazlqwQtG8yZ6zhQqnRLuhOXxcL8OwNoUejViJzV4RQSENeC7qWufOG+vm0/WdpMtLOBWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","last_reissued_at":"2026-05-17T23:38:46.118759Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.118759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation.","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Cheng Qian, Hanyang Chen, Heng Ji, Huan Zhang, Junyu Zhang, Kangrui Wang, Manling Li, Mark Zhao, Marziyeh Movahedi, Qineng Wang, Rui Yang, Teja Venkat Koripella, Tong Zhang","submitted_at":"2025-02-13T18:11:34Z","abstract_excerpt":"Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1,128 testing tasks across four environments, ranging from high-level semantic tasks (e.g., household) to low-level "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That performance in the four chosen simulated environments and the six curated capability subsets accurately reflects real-world embodied agent challenges.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EmbodiedBench is a new evaluation framework for MLLM-based embodied agents that shows strong high-level reasoning but weak low-level manipulation performance across 24 tested models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"24d1e1932f2590145c6de98df8201652f8faa79ced178991771771b68ff539dd"},"source":{"id":"2502.09560","kind":"arxiv","version":3},"verdict":{"id":"d69d70eb-fed1-4717-b23e-fcdbc2241a6c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:20:32.985543Z","strongest_claim":"MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average.","one_line_summary":"EmbodiedBench is a new evaluation framework for MLLM-based embodied agents that shows strong high-level reasoning but weak low-level manipulation performance across 24 tested models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That performance in the four chosen simulated environments and the six curated capability subsets accurately reflects real-world embodied agent challenges.","pith_extraction_headline":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation."},"references":{"count":22,"sample":[{"doi":"10.24963/ijcai.2024/15","year":2015,"title":"Put washed lettuce in the refrigerator","work_id":"8a8d949d-2daa-4325-9b00-2d5fadb84f24","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"**Visibility**: Always locate a visible object by the ’find’ action before interacting with it","work_id":"27f6b323-77d3-4db3-8a1a-0133d997f45e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Avoid performing actions that do not meet the defined validity criteria","work_id":"e891d1fa-8be9-43c7-b502-497cd9c17bb7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"You can explore these instances if you do not find the desired object in the current receptacle","work_id":"fd9c53ba-b5d9-4cb8-b73f-c6443a7c9b8a","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"If the last action is invalid, reflect on the reason, such as not adhering to action rules or missing preliminary actions, and adjust your plan accordingly","work_id":"96cd5e15-7387-45f4-8068-6e674c6a1dcb","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":22,"snapshot_sha256":"7fea875e5acea7790ca94317fbd59aa4120c82214e29dfcc91a73c550e611881","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0665e50e19214462b0da29e46b6e709c5809d5acf3f499f8d81c2f614a80fa8c"},"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":"2502.09560","created_at":"2026-05-17T23:38:46.118844+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09560v3","created_at":"2026-05-17T23:38:46.118844+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09560","created_at":"2026-05-17T23:38:46.118844+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHQVCX474M63","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHQVCX474M63G67R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHQVCX47","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":29,"sample":[{"citing_arxiv_id":"2601.21692","citing_title":"TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17776","citing_title":"CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17933","citing_title":"AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17776","citing_title":"CosFly-Track: A Large-Scale Multi-Modal Dataset for UAV Visual Tracking via Multi-Constraint Trajectory Optimization","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03438","citing_title":"Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08392","citing_title":"ST-BiBench: Benchmarking Multi-Stream Multimodal Coordination in Bimanual Embodied Tasks for MLLMs","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?","ref_index":91,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16331","citing_title":"BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07594","citing_title":"MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14704","citing_title":"SceneFunRI: Reasoning the Invisible for Task-Driven Functional Object Localization","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":124,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":113,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08747","citing_title":"Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06230","citing_title":"Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19839","citing_title":"Environmental Understanding Vision-Language Model for Embodied Agent","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11411","citing_title":"Online Reasoning Video Object Segmentation","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06230","citing_title":"Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07594","citing_title":"MemCompiler: Compile, Don't Inject -- State-Conditioned Memory for Embodied Agents","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07378","citing_title":"Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2","json":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2.json","graph_json":"https://pith.science/api/pith-number/HHQVCX474M63G67R7LUOLOWFX2/graph.json","events_json":"https://pith.science/api/pith-number/HHQVCX474M63G67R7LUOLOWFX2/events.json","paper":"https://pith.science/paper/HHQVCX47"},"agent_actions":{"view_html":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2","download_json":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2.json","view_paper":"https://pith.science/paper/HHQVCX47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09560&json=true","fetch_graph":"https://pith.science/api/pith-number/HHQVCX474M63G67R7LUOLOWFX2/graph.json","fetch_events":"https://pith.science/api/pith-number/HHQVCX474M63G67R7LUOLOWFX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/action/storage_attestation","attest_author":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/action/author_attestation","sign_citation":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/action/citation_signature","submit_replication":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/action/replication_record"}},"created_at":"2026-05-17T23:38:46.118844+00:00","updated_at":"2026-05-17T23:38:46.118844+00:00"}