{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HHQVCX474M63G67R7LUOLOWFX2","short_pith_number":"pith:HHQVCX47","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"},"canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","source":{"kind":"arxiv","id":"2502.09560","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09560","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09560v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09560","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"HHQVCX474M63","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HHQVCX474M63G67R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HHQVCX47","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HHQVCX474M63G67R7LUOLOWFX2","target":"record","payload":{"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"},"canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","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"},"source_kind":"arxiv","source_id":"2502.09560","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IxEq46hDIjW49iFZMLPGLpWHL8qOlFXIqwtQKzTr/KEcpAOTY88gYtgGRrw0q8hz713v8urtLC8fH/2QnPddAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:08:27.277754Z"},"content_sha256":"678f6f86a6ace2dedab86c4e354a8944d4a9cc3838d3292e4572cd5540838fc1","schema_version":"1.0","event_id":"sha256:678f6f86a6ace2dedab86c4e354a8944d4a9cc3838d3292e4572cd5540838fc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HHQVCX474M63G67R7LUOLOWFX2","target":"graph","payload":{"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"},"verdict_id":"d69d70eb-fed1-4717-b23e-fcdbc2241a6c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HH8ZHu8qjKxxzQt23GwtLLxuGn4aAkIC+tcUsILUJGi3v38Lkn2TQifmTuxFbizvw02qyR3dgzvkXpmafGF3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:08:27.278401Z"},"content_sha256":"87285d2d13c38948ff3ab0e97bfae1c219ec451cda2f01e553a088b03c38fbd2","schema_version":"1.0","event_id":"sha256:87285d2d13c38948ff3ab0e97bfae1c219ec451cda2f01e553a088b03c38fbd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/bundle.json","state_url":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHQVCX474M63G67R7LUOLOWFX2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T13:08:27Z","links":{"resolver":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2","bundle":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/bundle.json","state":"https://pith.science/pith/HHQVCX474M63G67R7LUOLOWFX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHQVCX474M63G67R7LUOLOWFX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HHQVCX474M63G67R7LUOLOWFX2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"12cbdefdd1c0e9a1766ce06a931d3e50de0b2822ea302800d0d69603632a1381","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T18:11:34Z","title_canon_sha256":"f197cab08bcf541567652650012478e17043804ab59a7cb2839f5e4a50c9323a"},"schema_version":"1.0","source":{"id":"2502.09560","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09560","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09560v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09560","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"HHQVCX474M63","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"HHQVCX474M63G67R","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"HHQVCX47","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:87285d2d13c38948ff3ab0e97bfae1c219ec451cda2f01e553a088b03c38fbd2","target":"graph","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That performance in the four chosen simulated environments and the six curated capability subsets accurately reflects real-world embodied agent challenges."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation."}],"snapshot_sha256":"24d1e1932f2590145c6de98df8201652f8faa79ced178991771771b68ff539dd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0665e50e19214462b0da29e46b6e709c5809d5acf3f499f8d81c2f614a80fa8c"},"paper":{"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 ","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","cross_cats":["cs.CL","cs.CV"],"headline":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T18:11:34Z","title":"EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents"},"references":{"count":22,"internal_anchors":0,"resolved_work":22,"sample":[{"cited_arxiv_id":"","doi":"10.24963/ijcai.2024/15","is_internal_anchor":false,"ref_index":1,"title":"Put washed lettuce in the refrigerator","work_id":"8a8d949d-2daa-4325-9b00-2d5fadb84f24","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"**Visibility**: Always locate a visible object by the ’find’ action before interacting with it","work_id":"27f6b323-77d3-4db3-8a1a-0133d997f45e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Avoid performing actions that do not meet the defined validity criteria","work_id":"e891d1fa-8be9-43c7-b502-497cd9c17bb7","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":7,"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","year":null}],"snapshot_sha256":"7fea875e5acea7790ca94317fbd59aa4120c82214e29dfcc91a73c550e611881"},"source":{"id":"2502.09560","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T00:20:32.985543Z","id":"d69d70eb-fed1-4717-b23e-fcdbc2241a6c","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"MLLMs excel at high-level embodied tasks but score only 28.9 percent on low-level manipulation.","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.","weakest_assumption":"That performance in the four chosen simulated environments and the six curated capability subsets accurately reflects real-world embodied agent challenges."}},"verdict_id":"d69d70eb-fed1-4717-b23e-fcdbc2241a6c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:678f6f86a6ace2dedab86c4e354a8944d4a9cc3838d3292e4572cd5540838fc1","target":"record","created_at":"2026-05-17T23:38:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"12cbdefdd1c0e9a1766ce06a931d3e50de0b2822ea302800d0d69603632a1381","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-13T18:11:34Z","title_canon_sha256":"f197cab08bcf541567652650012478e17043804ab59a7cb2839f5e4a50c9323a"},"schema_version":"1.0","source":{"id":"2502.09560","kind":"arxiv","version":3}},"canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39e1515f9fe33db37bf1fae8e5bac5be8bd65ad66c2761748c703d1323a40c9e","first_computed_at":"2026-05-17T23:38:46.118759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.118759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h6LkOdGVDzsGVTkwazlqwQtG8yZ6zhQqnRLuhOXxcL8OwNoUejViJzV4RQSENeC7qWufOG+vm0/WdpMtLOBWCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.119250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09560","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:678f6f86a6ace2dedab86c4e354a8944d4a9cc3838d3292e4572cd5540838fc1","sha256:87285d2d13c38948ff3ab0e97bfae1c219ec451cda2f01e553a088b03c38fbd2"],"state_sha256":"3e079a9bb05768e568fdf2f895ccb3e303280a843c5e6955cd66ed678118f2ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cL4vqrePqcZoo1DuzZAb/WeMBWTCgOtk6IeLe3IvwHrfW3cbC8dI6cmmRUO+aQxQ50uNO2gh3+O6ULnTy30nAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:08:27.281360Z","bundle_sha256":"0f39844bb262370fcc63f4abc763aa7f7025a896640cd58c0dd4fd048a30b647"}}