{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T19:44:48Z","timestamp":1792093488509,"version":"4.4.0"},"reference-count":292,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Scientific Research Innovation Capability Support Project for Young Faculty","award":["ZYGXQNJSKYCXNLZCXM-I28"],"award-info":[{"award-number":["ZYGXQNJSKYCXNLZCXM-I28"]}]},{"name":"Shenzhen Science and Technology Program","award":["QNXMA20250701093544048"],"award-info":[{"award-number":["QNXMA20250701093544048"]}]},{"name":"General Embodied AI Center of Sun Yat-sen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3703038","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T19:42:29Z","timestamp":1781293349000},"page":"12938-12957","source":"Crossref","is-referenced-by-count":2,"title":["Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5277-515X","authenticated-orcid":false,"given":"Kun","family":"Xiang","sequence":"first","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1271-4696","authenticated-orcid":false,"given":"Terry Jingchen","family":"Zhang","sequence":"additional","affiliation":[{"name":"ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinya","family":"Huang","sequence":"additional","affiliation":[{"name":"ETH AI Center, ETH Zurich","place":["Zurich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6663-685X","authenticated-orcid":false,"given":"Jixi","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zirong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueling","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhe","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijing","family":"Luo","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youpeng","family":"Wen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1301-1338","authenticated-orcid":false,"given":"Xiuwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9530","authenticated-orcid":false,"given":"Bingqian","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Yinwang Intelligent Technology Company, Ltd.","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-8972","authenticated-orcid":false,"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Yinwang Intelligent Technology Company, Ltd.","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9838-6532","authenticated-orcid":false,"given":"Hanhui","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1295-3362","authenticated-orcid":false,"given":"Bin","family":"Dong","sequence":"additional","affiliation":[{"name":"Peking University and Beijing International Center for Mathematical Research","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2455","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Ha"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10874-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.383"},{"key":"ref4","first-page":"4502","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Battaglia","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/085713-3130"},{"key":"ref6","first-page":"5083","article-title":"PHYRE: A new benchmark for physical reasoning","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Bakhtin","year":"2019"},{"key":"ref7","first-page":"19","article-title":"I-PHYRE: Interactive physical reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/085713-3670"},{"key":"ref9","article-title":"LLMPhy: Parameter-identifiable physical reasoning combining large language models and physics engines","volume-title":"Proc. 29th Int. Conf. Artif. Intell. Statist.","author":"Cherian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3574322"},{"key":"ref11","first-page":"2713","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref12","first-page":"2920","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref13","first-page":"1024","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton","year":"2017"},{"key":"ref14","first-page":"4542","article-title":"Visual interaction networks: Learning a physics simulator from video","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Watters","year":"2017"},{"key":"ref15","first-page":"2186","article-title":"A compositional object-based approach to learning physical dynamics","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3914"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/085713-4091"},{"key":"ref18","article-title":"A physics-guided multimodal transformer path to weather and climate sciences","author":"Han","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1063\/1.5116183"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2019.112732"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/085713-2324"},{"key":"ref22","article-title":"AlphaDrive: Unleashing the power of VLMs in autonomous driving via reinforcement learning and reasoning","author":"Jiang","year":"2025"},{"key":"ref23","article-title":"AutoDrive-R$^{2}$2: Incentivizing reasoning and self-reflection capacity for VLA model in autonomous driving","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref24","article-title":"Reinforcement learning meets large language models: A survey of advancements and applications across the LLM lifecycle","author":"Liu","year":"2025"},{"key":"ref25","article-title":"Causal modeling of dynamical systems","author":"Bongers","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8088-8_18"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802099"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417795"},{"key":"ref29","first-page":"7847","article-title":"Scalable differentiable physics for learning and control","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Qiao","year":"2020"},{"key":"ref30","article-title":"GPT-4o system card","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref32","article-title":"OpenAI O1 system card","year":"2024"},{"key":"ref33","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref34","article-title":"Physics SuperNova: AI agent matches elite gold medalists at IPhO 2025","author":"Qiu","year":"2025"},{"key":"ref35","article-title":"Multimodal reasoning for science: Technical report and 1st place solution to the ICML 2025 SeePhys challenge","author":"Liang","year":"2025"},{"key":"ref36","article-title":"GAIA-1: A generative world model for autonomous driving","author":"Hu","year":"2023"},{"key":"ref37","first-page":"55","article-title":"DriveDreamer: Towards real-world-driven world models for autonomous driving","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Wang","year":"2024"},{"key":"ref38","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","author":"Kim","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103575"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246481"},{"key":"ref43","article-title":"Probing perceptual constancy in large vision language models","author":"Sun","year":"2025"},{"key":"ref44","article-title":"From perception to cognition: A survey of vision-language interactive reasoning in multimodal large language models","author":"Zhou","year":"2025"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3637037"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3649182"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/763"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.67"},{"key":"ref49","article-title":"Foundation model driven robotics: A comprehensive review","author":"Khan","year":"2025"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1140\/epjc\/s10052-025-14707-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3746449"},{"key":"ref52","article-title":"Generative physical AI in vision: A survey","author":"Liu","year":"2025"},{"key":"ref53","article-title":"Is SORA a world simulator? A comprehensive survey on general world models and beyond","author":"Zhu","year":"2024"},{"key":"ref54","article-title":"3D and 4D world modeling: A survey","author":"Kong","year":"2025"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau0323"},{"key":"ref56","article-title":"From 2D to 3D cognition: A brief survey of general world models","author":"Xie","year":"2025"},{"key":"ref57","article-title":"A survey on world models grounded in acoustic physical information","author":"Chen","year":"2025"},{"key":"ref58","article-title":"From efficient multimodal models to world models: A survey","author":"Mai","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tmech.2025.3574943"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_13"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ojvt.2025.3604823"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2025.3603693"},{"key":"ref63","article-title":"A survey: Learning embodied intelligence from physical simulators and world models","author":"Long","year":"2025"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref65","article-title":"Large model empowered embodied AI: A survey on decision-making and embodied learning","author":"Liang","year":"2025"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1542-8"},{"key":"ref67","article-title":"Toward embodied AGI: A review of embodied AI and the road ahead","author":"Wang","year":"2025"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref69","article-title":"A survey on robotics with foundation models: Toward embodied AI","author":"Xu","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/s23073762"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref73","article-title":"Qwen3-Omni technical report","author":"Xu","year":"2025"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112371"},{"key":"ref75","article-title":"View-invariant pixelwise anomaly detection in multi-object scenes with adaptive view synthesis","author":"Varghese","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3407588"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241297998"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66096-3_39"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02831"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00213"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0457"},{"key":"ref84","first-page":"31078","article-title":"Multi-SpatialMLLM: Multi-frame spatial understanding with multi-modal large language models","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Xu"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-37098-3_6"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.08.014"},{"key":"ref87","first-page":"31029","article-title":"SpatialScore: Towards comprehensive evaluation for spatial intelligence","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Wu"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758219"},{"key":"ref89","article-title":"MMSI-Bench: A benchmark for multi-image spatial intelligence","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2026"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00497"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1080\/00405000.2020.1757296"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01978"},{"key":"ref93","article-title":"Vision-based approach for food weight estimation from 2D images","author":"Wimalasiri","year":"2024"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.24132\/CSRN.3401.24"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889158"},{"key":"ref96","first-page":"11117","article-title":"SlotFormer: Unsupervised visual dynamics simulation with object-centric models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709168"},{"key":"ref98","article-title":"Physion: Evaluating physical prediction from vision in humans and machines","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Bear","year":"2021"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1167\/jov.23.9.5622"},{"key":"ref100","first-page":"61526","article-title":"ContPhy: Continuum physical concept learning and reasoning from videos","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng","year":"2024"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref102","first-page":"69849","article-title":"UGPhysics: A comprehensive benchmark for undergraduate physics reasoning with large language models","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","volume":"267","author":"Xu"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.52202\/085713-0044"},{"key":"ref104","article-title":"GPQA: A graduate-level Google-proof Q&A benchmark","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Rein","year":"2024"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.211"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.811"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.736"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref110","article-title":"LOCA-R: Near-perfect performance on the chinese physics olympiad 2025","author":"Jian","year":"2025"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevPhysEducRes.19.010132"},{"key":"ref112","article-title":"Steps are all you need: Rethinking STEM education with prompt engineering","author":"Addala","year":"2024"},{"key":"ref113","article-title":"Symbolic or numerical? understanding physics problem solving in reasoning LLMs","author":"Dan","year":"2025"},{"key":"ref114","article-title":"Knowledge graphs are all you need: Leveraging KGs in physics question answering","author":"Addala","year":"2024"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-ijcnlp.43"},{"key":"ref116","article-title":"ABench-Physics: Benchmarking physical reasoning in LLMs via high-difficulty and dynamic physics problems","author":"Zhang","year":"2025"},{"key":"ref117","first-page":"7308","article-title":"Grounding physical concepts of objects and events through dynamic visual reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.eacl-long.166"},{"key":"ref119","article-title":"P1-VL: Bridging visual perception and scientific reasoning in physics olympiads","author":"Luo","year":"2026"},{"key":"ref120","first-page":"11633","article-title":"CLEVRER: Collision events for video representation and reasoning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yi"},{"key":"ref121","article-title":"Learning neural causal models from unknown interventions","author":"Ke","year":"2020"},{"key":"ref122","first-page":"887","article-title":"Dynamic visual reasoning by learning differentiable physics models from video and language","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Ding","year":"2021"},{"key":"ref123","article-title":"CAUSAL3D: A comprehensive benchmark for causal learning from visual data","author":"Liu","year":"2025"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0563"},{"key":"ref125","article-title":"PhySense: Principle-based physics reasoning benchmarking for large language models","author":"Xu","year":"2025"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s00707-025-04325-6"},{"key":"ref127","article-title":"A multi-agent framework for physical laws discovery","author":"Hu","year":"2024"},{"key":"ref128","first-page":"1","article-title":"Contemporary symbolic regression methods and their relative performance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cava","year":"2021"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3423681"},{"key":"ref130","article-title":"Combining genetic algorithm and compressed sensing for features and operators selection in symbolic regression","author":"Mazheika","year":"2024"},{"key":"ref131","article-title":"Parsing the language of expression: Enhancing symbolic regression with domain-aware symbolic priors","author":"Huang","year":"2025"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-026-49762-y"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-026-10265-5"},{"key":"ref134","article-title":"The AI Scientist-v2: Workshop-level automated scientific discovery via agentic tree search","author":"Yamada","year":"2025"},{"key":"ref135","article-title":"Open source planning & control system with language agents for autonomous scientific discovery","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Xu","year":"2025"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2414074122"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1017\/flo.2025.10032"},{"key":"ref138","article-title":"Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange","author":"Wang","year":"2026"},{"key":"ref139","article-title":"From agent-only social networks to autonomous scientific research: Lessons from OpenClaw and Moltbook, and the architecture of ClawdLab and Beach.Science","author":"Weidener","year":"2026"},{"key":"ref140","first-page":"12138","article-title":"ScienceAgentBench: Toward rigorous assessment of language agents for data-driven scientific discovery","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0963"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1145\/3746449"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/360825.360839"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/357290.357293"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"key":"ref146","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2018"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3235591"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00014"},{"key":"ref150","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel","year":"2017"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00150"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61042.2026.00099"},{"key":"ref155","first-page":"43781","article-title":"Towards world simulator: Crafting physical commonsense-based benchmark for video generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Meng","year":"2025"},{"key":"ref156","first-page":"16215","article-title":"VideoPhy: Evaluating physical commonsense for video generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bansal"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.52202\/085713-1834"},{"key":"ref158","article-title":"Open-SORA: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref159","first-page":"55897","article-title":"CogVideoX: Text-tovideo diffusion models with an expert transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01149"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_21"},{"key":"ref163","article-title":"ProPhy: Progressive physical alignment for dynamic world simulation","author":"Wang","year":"2025"},{"key":"ref164","article-title":"Think before you diffuse: LLMs-guided physics-aware video generation","author":"Zhang","year":"2025"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.52202\/085713-5466"},{"key":"ref166","first-page":"25105","article-title":"VideoPoet: A large language model for zero-shot video generation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Kondratyuk"},{"key":"ref167","article-title":"Morpheus: Benchmarking physical reasoning of video generative models with real physical experiments","author":"Zhang","year":"2025"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3877.003.0009"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.19"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0810"},{"key":"ref171","first-page":"2492","article-title":"Multiview neural surface reconstruction by disentangling geometry and appearance","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Yariv","year":"2020"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00153"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01122"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073599"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.272"},{"key":"ref178","article-title":"Back to the features: DINO as a foundation for video world models","author":"Baldassarre","year":"2025"},{"key":"ref179","first-page":"28991","article-title":"How far is video generation from world model: A physical law perspective","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kang","year":"2025"},{"key":"ref180","article-title":"Brax\u2013A differentiable physics engine for large scale rigid body simulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Freeman","year":"2021"},{"key":"ref181","article-title":"NeoPhysix: An ultra fast 3D physical simulator as development tool for AI algorithms","author":"Fischer","year":"2024"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794358"},{"key":"ref183","article-title":"DEM-NeRF: A neuro-symbolic method for scientific discovery through physics-informed simulation","author":"Tan","year":"2025"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02571"},{"key":"ref185","article-title":"LagNetViP: A Lagrangian neural network for video prediction","volume-title":"Proc. Conf. Assoc. Advance. Artif. Intell.","author":"Allen-Blanchette","year":"2020"},{"key":"ref186","article-title":"FusionForce: End-to-end differentiable neural-symbolic layer for trajectory prediction","author":"Agishev","year":"2025"},{"key":"ref187","article-title":"PhyWorldBench: A comprehensive evaluation of physical realism in text-to-video models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu","year":"2026"},{"key":"ref188","article-title":"Vision-language-action models: Concepts, progress, applications and challenges","author":"Sapkota","year":"2025"},{"key":"ref189","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.025"},{"key":"ref191","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2021.3050609"},{"key":"ref193","first-page":"22698","article-title":"Flow matching for generative modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lipman"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1177\/02783649241273668"},{"key":"ref195","first-page":"6892","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. Int. Conf. Robot. Automat.","author":"O\u2019Neill","year":"2024"},{"key":"ref196","article-title":"World action models are zero-shot policies","author":"Ye","year":"2026"},{"key":"ref197","article-title":"World action verifier: Self-improving world models via forward-inverse asymmetry","author":"Liu","year":"2026"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-37718-0_19"},{"key":"ref199","article-title":"Active exploration for contact-rich tasks via online-adaptable models","volume-title":"Proc. Int. Conf. Robot. Automat.","author":"Ling","year":"2024"},{"key":"ref200","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ichter","year":"2022"},{"key":"ref201","article-title":"Active visuo-tactile interactive robotic perception for object property-aware manipulation","author":"Wu","year":"2023"},{"key":"ref202","first-page":"70576","article-title":"EmbodiedBench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2025"},{"key":"ref203","article-title":"EMMOE: A comprehensive benchmark for embodied mobile manipulation in open environments","author":"Li","year":"2025"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref205","article-title":"RoboSuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020"},{"key":"ref206","first-page":"2058","article-title":"ManiSkill2: A unified benchmark for generalizable manipulation skills","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref207","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Yu"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3180108"},{"key":"ref209","first-page":"477","article-title":"BEHAVIOR: Benchmark for everyday household activities in virtual, interactive, and ecological environments","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Srivastava"},{"key":"ref210","first-page":"11441","article-title":"GraspNet-1Billion: A large-scale benchmark for general object grasping","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn.","author":"Fang","year":"2020"},{"key":"ref211","article-title":"Vision-and-language navigation today and tomorrow: A survey in the era of foundation models","author":"Zhang","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref212","article-title":"Research on navigation methods based on LLMs","author":"Zhang","year":"2025"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref214","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Chaplot","year":"2020"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341827"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247308"},{"key":"ref217","article-title":"LGR: LLM-guided ranking of frontiers for object goal navigation","author":"Uno","year":"2025"},{"key":"ref218","article-title":"CL-CoTNav: Closed-loop hierarchical chain-of-thought for zero-shot object-goal navigation with vision-language models","author":"Cai","year":"2025"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3655265"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.229"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01496"},{"key":"ref222","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.018"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01074"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.327"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.32974"},{"key":"ref231","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4777514","article-title":"UNMuTe: Unifying navigation and multimodal dialogue-like text generation","author":"Rawal","year":"2024"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-0014-7_1"},{"key":"ref233","article-title":"Uncovering the fragility of trustworthy LLMs through chinese textual ambiguity","volume-title":"Proc. Agentic GenAI Eval. Workshop KDD\u201925","author":"Wu","year":"2025"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128692"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610450"},{"key":"ref236","article-title":"AI2-THOR: An interactive 3D environment for visual AI","author":"Kolve","year":"2017"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00323"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802709"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref245","first-page":"1384","article-title":"The RobotSlang benchmark: Dialog-guided robot localization and navigation","volume-title":"Proc. Conf. Robot Learn.","volume":"155","author":"Banerjee","year":"2021"},{"key":"ref246","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","volume":"100","author":"Thomason","year":"2020"},{"key":"ref247","article-title":"RoboRAN: A unified robotics framework for reinforcement learning-based autonomous navigation","author":"El-Hariry","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref248","article-title":"A framework for automated driving system testable cases and scenarios","author":"Thorn","year":"2018"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21918"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.177\/0278364920917446"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2016.2578706"},{"key":"ref252","article-title":"End to end learning for self-driving cars","author":"Bojarski","year":"2016"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.62.1805"},{"key":"ref254","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"LaValle","year":"1998","journal-title":"Res. Rep. 9811"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1016\/s0967-0661(02)00186-7"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1177\/027836498600500106"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.031"},{"key":"ref258","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","volume-title":"Proc. Conf. Assoc. Advance. Artif. Intell.","author":"Ziebart","year":"2008"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_32"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160609"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02496"},{"key":"ref263","article-title":"OccLLaMA: An occupancy-language-action generative world model for autonomous driving","author":"Wei","year":"2024"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33010"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160890"},{"key":"ref266","article-title":"DriveCoT: Integrating chain-of-thought reasoning with end-to-end driving","author":"Wang","year":"2024"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00526"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3626711"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247360"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref271","article-title":"TeraSim-World: Worldwide safety-critical data synthesis for end-to-end autonomous driving","author":"Wang","year":"2025"},{"key":"ref272","article-title":"Cosmos-drive-dreams: Scalable synthetic driving data generation with world foundation models","author":"Ren","year":"2025"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_9"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-08744-2"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3259322"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2017.7995802"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610077"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref280","first-page":"1","article-title":"CARLA: An open urban driving simulator","volume-title":"Proc. Conf. Robot Learn.","volume":"78","author":"Dosovitskiy","year":"2017"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188435"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0025"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-06255-3"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.3390\/s18082678"},{"key":"ref286","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"ref287","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref288","first-page":"624","article-title":"Learning particle dynamics for manipulating rigid bodies, deformable objects, and fluids","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref289","article-title":"Phi-4-Reasoning technical report","author":"Abdin","year":"2025"},{"key":"ref290","first-page":"9112","article-title":"Attention over learned object embeddings enables complex visual reasoning","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Ding","year":"2021"},{"key":"ref291","article-title":"Class-balanced grouping and sampling for point cloud 3D object detection","author":"Zhu","year":"2019"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00731"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11561107.pdf?arnumber=11561107","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:10:00Z","timestamp":1790262600000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11561107\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":292,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3703038","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}