Elamur Research⌕
☰
home / papers / 2026 / Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

Paper · 2026 · Wenqi Zhang, Mengna Wang, Gangao Liu et al.

Summary

Reasoning models do well at math and coding, but it is unclear whether they can handle embodied tasks. In these tasks an agent explores a room over many turns and must work with long sequences of alternating images and text. The authors present Embodied-Reasoner, a vision-language agent that combines visual search, step-by-step thinking and object interaction.

They built a data engine on the AI2-THOR simulator. It automatically creates Observation-Thought-Action trajectories, where each step's reasoning is grounded in what the agent actually sees. The engine also adds plausible exploratory detours, so the model learns to search rather than memorize where objects are.

Training has three stages:

  1. Imitation learning.
  2. Rejection-sampling tuning on the model's own exploration runs.
  3. Reflection tuning, which uses failed runs to teach self-correction.

On 809 unseen tasks, the model beats strong reasoning VLMs such as OpenAI o1 and o3-mini, with the largest gains on long composite tasks. It also repeats searches less often and contradicts itself less. This matters because it suggests that structured long-form reasoning can carry over from symbolic domains to interactive, perception-driven agents, including in real-world tests.

Key points

  • Dataset: 9,390 trajectories with about 64k first-person images and 90k reasoning segments. The segments follow five tagged thinking patterns: Situation Analysis, Spatial Reasoning, Planning, Reflection and Verification.
  • Environment and tasks: AI2-THOR with 120 indoor scenes and 2,100 objects. Tasks fall into four categories: Search, Transport, Manipulate and Composite. Actions are discrete and high-level rather than low-level motor control.
  • Main results: gains of +9% over o1 and +24% over o3-mini, and +39.9% on composite tasks. The reported margin over Claude-3.7 differs within the paper: +13% in the abstract and +22% in the introduction.
  • Ablations:
    • Without Stage 1, success drops from 81.0% to 19.1%.
    • Without Stage 2, success falls to 52.1%.
    • Stage 3 raises Composite success from 26.7% to 54.3%.
    • Merging the five patterns into a single <thinking> tag lowers Transport by 4.40 points and Composite by 6.77 points.
  • Memory-augmented variant: it uses compressed textual summaries plus an image retrieval buffer, trained with 50 hand-crafted trajectories. This cuts tokens per trajectory by about 90% (52k to 5.8k) while keeping success stable.
  • Code: github.com/zwq2018/embodied_reasoner

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🏢Alibaba GroupHangzhou · China168 works · 15,386 citations🎓Renmin University of ChinaBeijing · China114 works · 16,118 citations🎓Zhejiang UniversityHangzhou · China172 works · 12,988 citations🏛️Chinese Academy of SciencesBeijing · China194 works · 23,906 citations🎓University of Chinese Academy of SciencesBeijing · China147 works · 8,480 citations🏢Alibaba DAMO AcademyHangzhou · China39 works · 6,378 citations🏢Alibaba Group (Cayman Islands)George Town · Cayman Islands32 works · 3,389 citations🔬Institute of SoftwareBeijing · China21 works · 4,980 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputer Vision and Pattern Recognition · 2,869 worksEngineering · 133 worksControl and Systems Engineering · 45 works

🧭 Topics 1Research subjects and languages the work is about.Reasoning · 1,426 works

Cite

Cite as Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li and Yueting Zhuang. 2026. Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.1910

@inproceedings{zhang2026embodied,
  title = {{Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks}},
  author = {Wenqi Zhang, Mengna Wang, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li and Yueting Zhuang},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1910},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1910}
}

References

138 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Chuyuan Fu, Keerthana Gopalakrishnan, Karol Hausman, and 1 others. 2022. Do as i can, not as i say: Grounding language in robotic affordances. arXiv preprint arXiv:2204.01691.
  2. Dong An, Hanqing Wang, Wenguan Wang, Zun Wang, Yan Huang, Keji He, and Liang Wang. 2024. Etpnav: Evolving topological planning for vision-language navigation in continuous environments. IEEE Transactions on Pattern Analysis and Machine Intelligence. find
  3. Peter Anderson, Qi Wu, Damien Teney, Jake Bruce, Mark Johnson, Niko Sünderhauf, Ian Reid, Stephen Gould, and Anton Van Den Hengel. 2018. Vision-and-language navigation: Interpreting visually-grounded navigation instructions in real environments. In Proceedings of the IEEE conference on computer visi…
  4. Berk Calli, Arjun Singh, Aaron Walsman, Siddhartha Srinivasa, Pieter Abbeel, and Aaron M Dollar. 2015. The ycb object and model set: Towards common benchmarks for manipulation research. In 2015 international conference on advanced robotics (ICAR), pages 510–517. IEEE. find
  5. Angel Chang, Angela Dai, Thomas Funkhouser, Maciej Halber, Matthias Nießner, Manolis Savva, Shuran Song, Andy Zeng, and Yinda Zhang. 2017. Matterport3d: Learning from rgb-d data in indoor environments. Preprint, arXiv:1709.06158. — [arXiv:1709.06158](https://arxiv.org/abs/1709.06158) find
  6. Jiaqi Chen, Bingqian Lin, Ran Xu, Zhenhua Chai, Xiaodan Liang, and Kwan-Yee Wong. 2024. Mapgpt: Map-guided prompting with adaptive path planning for vision-and-language navigation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pag… find
  7. Anthropic. 2025. Claude 3.7 sonnet: Anthropic’s hybrid reasoning ai model. find
  8. Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478.
  9. Alisson Azzolini, Junjie Bai, Hannah Brandon, Jiaxin Cao, Prithvijit Chattopadhyay, Huayu Chen, Jinju Chu, Yin Cui, Jenna Diamond, Yifan Ding, and 1 others. 2025. Cosmos-reason1: From physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558. — [arXiv:2503.15558](https://arxiv.org/abs/2503.15558) find
  10. Kevin Chen, Junshen K Chen, Jo Chuang, Marynel Vázquez, and Silvio Savarese. 2021a. Topological planning with transformers for vision-and-language navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11276–11286. find
  11. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, and 1 others. 2025. Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923. — Qwen2.5-VL Technical Report
  12. Peihao Chen, Dongyu Ji, Kunyang Lin, Runhao Zeng, Thomas Li, Mingkui Tan, and Chuang Gan. 2022a. Weakly-supervised multi-granularity map learning for vision-and-language navigation. Advances in Neural Information Processing Systems, 35:38149– 38161. find
  13. Anthropic. 2024. Claude 3.5-sonnet: Anthropic’s advanced language model. find
  14. Kevin Black, Noah Brown, Danny Driess, Adnan Esmail, Michael Equi, Chelsea Finn, Niccolo Fusai, Lachy Groom, Karol Hausman, Brian Ichter, and 1 others. 2024. pi-0: A vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164. find
  15. Valts Blukis, Chris Paxton, Dieter Fox, Animesh Garg, and Yoav Artzi. 2022. A persistent spatial semantic representation for high-level natural language instruction execution. In Conference on Robot Learning, pages 706–717. PMLR. find
  16. Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, and 1 others. 2023. Rt-2: Vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818. find
  17. Shaofei Cai, Zihao Wang, Kewei Lian, Zhancun Mu, Xiaojian Ma, Anji Liu, and Yitao Liang. 2024. Rocket-1: Mastering open-world interaction with Shizhe Chen, Pierre-Louis Guhur, Cordelia Schmid, and Ivan Laptev. 2021b. History aware multimodal transformer for vision-and-language navigation. Advances i… find
  18. Shizhe Chen, Pierre-Louis Guhur, Makarand Tapaswi, Cordelia Schmid, and Ivan Laptev. 2022b. Think global, act local: Dual-scale graph transformer for vision-and-language navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16537–16547. find
  19. Zhe Chen, Weiyun Wang, Yue Cao, Yangzhou Liu, Zhangwei Gao, Erfei Cui, Jinguo Zhu, Shenglong Ye, Hao Tian, Zhaoyang Liu, Lixin Gu, Xuehui Wang, Qingyun Li, Yiming Ren, Zixuan Chen, Jiapeng Luo, Jiahao Wang, Tan Jiang, Bo Wang, and 23 others. 2025. Expanding performance boundaries of open-source mult…
  20. An-Chieh Cheng, Yandong Ji, Zhaojing Yang, Zaitian Gongye, Xueyan Zou, Jan Kautz, Erdem Bıyık, Hongxu Yin, Sifei Liu, and Xiaolong Wang. 2024. Navila: Legged robot vision-language-action model for navigation. arXiv preprint arXiv:2412.04453. — [arXiv:2412.04453](https://arxiv.org/abs/2412.04453) find
  21. Reinis Cimurs, Il Hong Suh, and Jin Han Lee. 2021. Goal-driven autonomous exploration through deep reinforcement learning. IEEE Robotics and Automation Letters, 7(2):730–737. find
  22. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  23. InternNav Contributors. 2025. InternNav: Intern-Robotics’ open platform for building generalized navigation foundation models. https://github.com/ InternRobotics/InternNav. ↗
  24. Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino, Arun Ahuja, Sheila Babayan, Felix Hill, and Rob Fergus. 2023. Collaborating with language models for embodied reasoning. arXiv preprint arXiv:2302.00763. find
  25. DeepMind. 2025. Flash thinking. find
  26. Matt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs, Kiana Ehsani, Jordi Salvador, Winson Han, Eric Kolve, Aniruddha Kembhavi, and Roozbeh Mottaghi. 2022. Procthor: Large-scale embodied ai using procedural generation. Advances in Neural Information Processing Systems, 35:5982–5994. find
  27. Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, and 1 others. 2023. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378. find
  28. Yifan Du, Zikang Liu, Yifan Li, Wayne Xin Zhao, Yuqi Huo, Bingning Wang, Weipeng Chen, Zheng Liu, Zhongyuan Wang, and Ji-Rong Wen. 2025. Virgo: A preliminary exploration on reproducing o1-like mllm. arXiv preprint arXiv:2501.01904. — [arXiv:2501.01904](https://arxiv.org/abs/2501.01904) find
  29. Kiana Ehsani, Tanmay Gupta, Rose Hendrix, Jordi Salvador, Luca Weihs, Kuo-Hao Zeng, Kunal Pratap Singh, Yejin Kim, Winson Han, Alvaro Herrasti, and 1 others. 2024. Spoc: Imitating shortest paths in simulation enables effective navigation and manipulation in the real world. In Proceedings of the IEEE… find
  30. Kiana Ehsani, Winson Han, Alvaro Herrasti, Eli VanderBilt, Luca Weihs, Eric Kolve, Aniruddha Kembhavi, and Roozbeh Mottaghi. 2021. Manipulathor: A framework for visual object manipulation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4497–4506. find
  31. Georgios Georgakis, Karl Schmeckpeper, Karan Wan-choo, Soham Dan, Eleni Miltsakaki, Dan Roth, and Kostas Daniilidis. 2022. Cross-modal map learning for vision and language navigation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15460–15470. find
  32. Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, and Mao Yang. 2025. rstar-math: Small llms can master math reasoning with self-evolved deep thinking. arXiv preprint arXiv:2501.04519.
  33. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  34. Jarvis Guo, Tuney Zheng, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Yizhi Li, Graham Neubig, Wenhu Chen, and Xiang Yue. 2024. Mammoth-vl: Eliciting multimodal reasoning with instruction tuning at scale. arXiv preprint arXiv:2412.05237.
  35. Yicong Hong, Zun Wang, Qi Wu, and Stephen Gould. 2022. Bridging the gap between learning in discrete and continuous environments for vision-and-language navigation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15439–15449. find
  36. Chenguang Huang, Oier Mees, Andy Zeng, and Wolfram Burgard. 2022a. Visual language maps for robot navigation. arXiv preprint arXiv:2210.05714. — [arXiv:2210.05714](https://arxiv.org/abs/2210.05714) find
  37. Chenguang Huang, Oier Mees, Andy Zeng, and Wolfram Burgard. 2023a. Visual language maps for robot navigation. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 10608– 10615. IEEE. find
  38. Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, and Siyuan Huang. 2023b. An embodied generalist agent in 3d world. arXiv preprint arXiv:2311.12871. — [arXiv:2311.12871](https://arxiv.org/abs/2311.12871) find
  39. Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022b. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning, pages 9118–9147. PMLR.
  40. Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, and 1 others. 2022c. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:2207.05608. find
  41. Wenxuan Huang, Bohan Jia, Zijie Zhai, Shaosheng Cao, Zheyu Ye, Fei Zhao, Zhe Xu, Yao Hu, and Shaohui Lin. 2025a. Vision-r1: Incentivizing reasoning capability in multimodal large language models. arXiv preprint arXiv:2503.06749. find
  42. Zhongzhen Huang, Gui Geng, Shengyi Hua, Zhen Huang, Haoyang Zou, Shaoting Zhang, Pengfei Liu, and Xiaofan Zhang. 2025b. O1 replication journey– part 3: Inference-time scaling for medical reasoning. arXiv preprint arXiv:2501.06458. — [arXiv:2501.06458](https://arxiv.org/abs/2501.06458) find
  43. Bingqian Lin, Yunshuang Nie, Ziming Wei, Jiaqi Chen, Shikui Ma, Jianhua Han, Hang Xu, Xiaojun Chang, and Xiaodan Liang. 2025. Navcot: Boosting llm-based vision-and-language navigation via learning disentangled reasoning. Preprint, arXiv:2403.07376. — [arXiv:2403.07376](https://arxiv.org/abs/2403.07376) find
  44. Shyam Sundar Kannan, Vishnunandan LN Venkatesh, and Byung-Cheol Min. 2024. Smart-llm: Smart multi-agent robot task planning using large language models. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 12140–12147. IEEE. find
  45. Kevin Lin, Christopher Agia, Toki Migimatsu, Marco Pavone, and Jeannette Bohg. 2023. Text2motion: From natural language instructions to feasible plans. Autonomous Robots, 47(8):1345–1365. find
  46. Mukul Khanna, Ram Ramrakhya, Gunjan Chhablani, Sriram Yenamandra, Theophile Gervet, Matthew Chang, Zsolt Kira, Devendra Singh Chaplot, Dhruv Batra, and Roozbeh Mottaghi. 2024. Goat-bench: A benchmark for multi-modal lifelong navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision an… find
  47. Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Foster, Grace Lam, Pannag Sanketi, and 1 others. 2024. Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246. find
  48. Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Matt Deitke, Kiana Ehsani, Daniel Gordon, Yuke Zhu, and 1 others. 2017. Ai2-thor: An interactive 3d environment for visual ai. arXiv preprint arXiv:1712.05474. find
  49. Jacob Krantz, Erik Wijmans, Arjun Majumdar, Dhruv Batra, and Stefan Lee. 2020. Beyond the nav-graph: Vision-and-language navigation in continuous environments. In European Conference on Computer Vision, pages 104–120. Springer. find
  50. Jonáš Kulhánek, Erik Derner, Tim De Bruin, and Robert Babuška. 2019. Vision-based navigation using deep reinforcement learning. In 2019 european conference on mobile robots (ECMR), pages 1–8. IEEE. find
  51. Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Martín-Martín, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun, and 1 others. 2023. Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In Conference on Robot Lear… find
  52. Manling Li, Shiyu Zhao, Qineng Wang, Kangrui Wang, Yu Zhou, Sanjana Srivastava, Cem Gokmen, Tony Lee, Li E Li, Ruohan Zhang, and 1 others. 2024. Embodied agent interface: Benchmarking llms for embodied decision making. Advances in Neural Information Processing Systems, 37:100428–100534. find
  53. Jacky Liang, Wenlong Huang, Fei Xia, Peng Xu, Karol Hausman, Brian Ichter, Pete Florence, and Andy Zeng. 2023. Code as policies: Language model programs for embodied control. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 9493–9500. IEEE. find
  54. Yuxing Long, Xiaoqi Li, Wenzhe Cai, and Hao Dong. 2023. Discuss before moving: Visual language navigation via multi-expert discussions. Preprint, arXiv:2309.11382. — [arXiv:2309.11382](https://arxiv.org/abs/2309.11382) find
  55. Arjun Majumdar, Anurag Ajay, Xiaohan Zhang, Pranav Putta, Sriram Yenamandra, Mikael Henaff, Sneha Silwal, Paul Mcvay, Oleksandr Maksymets, Sergio Arnaud, and 1 others. 2024. Openeqa: Embodied question answering in the era of foundation models. In Proceedings of the IEEE/CVF conference on computer vi… find
  56. Meta. 2025. The llama 4 herd: The beginning of a new era of natively multimodal ai innovation. find
  57. Meta AI. 2024. Llama 3.2: Revolutionizing edge ai and vision with open, customizable models. Meta Blog. Accessed: 2026-01-06. find
  58. So Yeon Min, Devendra Singh Chaplot, Pradeep Ravikumar, Yonatan Bisk, and Ruslan Salakhutdinov. 2021. Film: Following instructions in language with modular methods. arXiv preprint arXiv:2110.07342. find
  59. Yingqian Min, Zhipeng Chen, Jinhao Jiang, Jie Chen, Jia Deng, Yiwen Hu, Yiru Tang, Jiapeng Wang, Xiaoxue Cheng, Huatong Song, and 1 others. 2024. Imitate, explore, and self-improve: A reproduction report on slow-thinking reasoning systems. arXiv preprint arXiv:2412.09413. find
  60. Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, and Ping Luo. 2023. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems, 36:25081–25094. find
  61. Michael Murray and Maya Cakmak. 2022. Following natural language instructions for household tasks with landmark guided search and reinforced pose adjustment. IEEE Robotics and Automation Letters, 7(3):6870–6877. find
  62. OpenAI. 2024a. Gpt-4o mini: advancing cost-efficient intelligence. find
  63. OpenAI. 2024b. Gpt-4o: Openai’s multimodal language model. find
  64. OpenAI. 2024c. Openai o1: Advanced reasoning ai model. find
  65. OpenAI. 2025. o3-mini: Openai’s advanced reasoning model. find
  66. Bowen Pan, Rameswar Panda, SouYoung Jin, Rogerio Feris, Aude Oliva, Phillip Isola, and Yoon Kim. 2024. Langnav: Language as a perceptual representation for navigation. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 950– 974. find
  67. Akhil Perincherry, Jacob Krantz, and Stefan Lee. 2025. Do visual imaginations improve vision-and-language navigation agents? Preprint, arXiv:2503.16394. — [arXiv:2503.16394](https://arxiv.org/abs/2503.16394) find
  68. Xavier Puig, Eric Undersander, Andrew Szot, Mikael Dallaire Cote, Tsung-Yen Yang, Ruslan Part-sey, Ruta Desai, Alexander William Clegg, Michal Hlavac, So Yeon Min, and 1 others. 2023. Habitat 3.0: A co-habitat for humans, avatars and robots. arXiv preprint arXiv:2310.13724. — [arXiv:2310.13724](https://arxiv.org/abs/2310.13724) find
  69. Yanyuan Qiao, Wenqi Lyu, Hui Wang, Zixu Wang, Zerui Li, Yuan Zhang, Mingkui Tan, and Qi Wu. 2025. Open-nav: Exploring zero-shot vision-and-language navigation in continuous environment with open-source llms. In 2025 IEEE International Conference on Robotics and Automation (ICRA), pages 6710–6717. IE… find
  70. Yanyuan Qiao, Yuankai Qi, Zheng Yu, Jing Liu, and Qi Wu. 2023. March in chat: Interactive prompting for remote embodied referring expression. In Proceedings of the IEEE/CVF international conference on computer vision, pages 15758–15767. find
  71. Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, and 1 others. 2024. O1 replication journey: A strategic progress report–part 1. arXiv preprint arXiv:2410.18982. find
  72. Delin Qu, Haoming Song, Qizhi Chen, Yuanqi Yao, Xinyi Ye, Yan Ding, Zhigang Wang, JiaYuan Gu, Bin Zhao, Dong Wang, and 1 others. 2025. Spatialvla: Exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830. — [arXiv:2501.15830](https://arxiv.org/abs/2501.15830) find
  73. QwenLM. 2025. Qvq-72b preview. find
  74. Sonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, and Angel Chang. 2021. Language-aligned waypoint (law) supervision for vision-and-language navigation in continuous environments. In Proceedings of the 2021 conference on empirical methods in natural language processing, pages 4018–4028. find
  75. Dhruv Shah, Błażej Osiński, Sergey Levine, and 1 others. 2023. Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action. In Conference on robot learning, pages 492–504. PMLR. find
  76. Yongliang Shen, Kaitao Song, Xu Tan, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu, Dongsheng Li, and Yueting Zhuang. 2023. Taskbench: Benchmarking large language models for task automation. arXiv preprint arXiv:2311.18760. — [arXiv:2311.18760](https://arxiv.org/abs/2311.18760) find
  77. Lucy Xiaoyang Shi, Brian Ichter, Michael Equi, Liyiming Ke, Karl Pertsch, Quan Vuong, James Tanner, Anna Walling, Haohuan Wang, Niccolo Fusai, and 1 others. 2025a. Hi robot: Open-ended instruction following with hierarchical vision-language-action models. arXiv preprint arXiv:2502.19417. — [arXiv:2502.19417](https://arxiv.org/abs/2502.19417) find
  78. Xiangyu Shi, Zerui Li, Wenqi Lyu, Jiatong Xia, Feras Dayoub, Yanyuan Qiao, and Qi Wu. 2025b. Smart-way: Enhanced waypoint prediction and backtracking for zero-shot vision-and-language navigation. Preprint, arXiv:2503.10069. — [arXiv:2503.10069](https://arxiv.org/abs/2503.10069) find
  79. Xiangyu Shi, Zerui Li, Yanyuan Qiao, and Qi Wu. 2025c. Fast-smartway: Panoramic-free end-to-end zero-shot vision-and-language navigation. Preprint, arXiv:2511.00933. — [arXiv:2511.00933](https://arxiv.org/abs/2511.00933) find
  80. Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. Alfred: A benchmark for interpreting grounded instructions for everyday tasks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, page…
  81. Kunal Pratap Singh, Suvaansh Bhambri, Byeonghwi Kim, Roozbeh Mottaghi, and Jonghyun Choi. 2021. Factorizing perception and policy for interactive instruction following. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1888–1897. find
  82. Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M Sadler, Wei-Lun Chao, and Yu Su. 2023. Llm-planner: Few-shot grounded planning for embodied agents with large language models. In Proceedings of the IEEE/CVF international conference on computer vision, pages 2998–3009.
  83. Gabriel Sarch, Yue Wu, Michael J Tarr, and Katerina Fragkiadaki. 2023. Open-ended instructable embodied agents with memory-augmented large language models. arXiv preprint arXiv:2310.15127. find
  84. Andrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Singh Chaplot, Oleksandr Maksymets, and 1 others. 2021. Habitat 2.0: Training home assistants to rearrange their habitat. Advances in neural information processing systems, 3… find
  85. Manolis Savva, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, Vladlen Koltun, Jitendra Malik, Devi Parikh, and Dhruv Batra. 2019. Habitat: A platform for embodied ai research. Preprint, arXiv:1904.01201. find
  86. Gemini Robotics Team, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Travis Armstrong, Ashwin Balakrishna, Robert Baruch, Maria Bauza, Michiel Blokzijl, Steven Bohez, Konstantinos Bousmalis, Anthony Brohan, Thomas Buschmann, Arunkumar Byravan, Serkan Cabi, Ken… find
  87. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… find
  88. InternVLA-N1 Team. 2025a. InternVLA-N1: An open dual-system navigation foundation model with learned latent plans. find
  89. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, and 1 others. 2025c. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599. — Kimi k1.5: Scaling Reinforcement Learning with LLMs
  90. Octo Model Team, Dibya Ghosh, Homer Walke, Karl Pertsch, Kevin Black, Oier Mees, Sudeep Dasari, Joey Hejna, Tobias Kreiman, Charles Xu, and 1 others. 2024. Octo: An open-source generalist robot policy. arXiv preprint arXiv:2405.12213. find
  91. Qwen Team. 2024. Qwq: Reflect deeply on the boundaries of the unknown. find
  92. Qwen Team. 2025b. Qwen-vl-max: Alibaba cloud’s advanced large vision language model. find
  93. Omkar Thawakar, Dinura Dissanayake, Ketan More, Ritesh Thawkar, Ahmed Heakl, Noor Ahsan, Yuhao Li, Mohammed Zumri, Jean Lahoud, Rao Muhammad Anwer, and 1 others. 2025. Llamav-o1: Rethinking step-by-step visual reasoning in llms. arXiv preprint arXiv:2501.06186. find
  94. Sai H Vemprala, Rogerio Bonatti, Arthur Bucker, and Ashish Kapoor. 2024. Chatgpt for robotics: Design principles and model abilities. Ieee Access. find
  95. Naoki Wake, Atsushi Kanehira, Kazuhiro Sasabuchi, Jun Takamatsu, and Katsushi Ikeuchi. 2024. Gpt-4v (ision) for robotics: Multimodal task planning from human demonstration. IEEE Robotics and Automation Letters. find
  96. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023a. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291. find
  97. Hanqing Wang, Wei Liang, Luc Van Gool, and Wenguan Wang. 2023b. Dreamwalker: Mental planning for continuous vision-language navigation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10873–10883. find
  98. Hanqing Wang, Wenguan Wang, Wei Liang, Caiming Xiong, and Jianbing Shen. 2021. Structured scene memory for vision-language navigation. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 8455–8464. find
  99. Jiaqi Wang, Enze Shi, Huawen Hu, Chong Ma, Yiheng Liu, Xuhui Wang, Yincheng Yao, Xuan Liu, Bao Ge, and Shu Zhang. 2024a. Large language models for robotics: Opportunities, challenges, and perspectives. Journal of Automation and Intelligence. find
  100. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, and 1 others. 2024b. Qwen2-vl: Enhancing vision-language model’s perception of the world at any resolution. arXiv preprint arXiv:2409.12191.
  101. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560. find
  102. Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, and Shuqiang Jiang. 2023c. Gridmm: Grid memory map for vision-and-language navigation. In Proceedings of the IEEE/CVF International conference on computer vision, pages 15625–15636. find
  103. Meng Wei, Chenyang Wan, Jiaqi Peng, Xiqian Yu, Yuqiang Yang, Delin Feng, Wenzhe Cai, Chenming Zhu, Tai Wang, Jiangmiao Pang, and Xihui Liu. 2025a. Ground slow, move fast: A dual-system foundation model for generalizable vision-and-language navigation. Preprint, arXiv:2512.08186. — [arXiv:2512.08186](https://arxiv.org/abs/2512.08186) find
  104. Meng Wei, Chenyang Wan, Xiqian Yu, Tai Wang, Yuqiang Yang, Xiaohan Mao, Chenming Zhu, Wenzhe Cai, Hanqing Wang, Yilun Chen, Xihui Liu, and Jiangmiao Pang. 2025b. Streamvln: Streaming vision-and-language navigation via slowfast context modeling. Preprint, arXiv:2507.05240. — [arXiv:2507.05240](https://arxiv.org/abs/2507.05240) find
  105. Luca Weihs, Matt Deitke, Aniruddha Kembhavi, and Roozbeh Mottaghi. 2021. Visual room rearrangement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5922–5931. find
  106. Junjie Wen, Yichen Zhu, Minjie Zhu, Jinming Li, Zhiyuan Xu, Zhengping Che, Chaomin Shen, Yaxin Peng, Dong Liu, Feifei Feng, and 1 others. 2024. Object-centric instruction augmentation for robotic manipulation. In 2024 IEEE International Conference on Robotics and Automation (ICRA), pages 4318–4325.… find
  107. Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, and Haibin Yan. 2023. Embodied task planning with large language models. arXiv preprint arXiv:2307.01848. — [arXiv:2307.01848](https://arxiv.org/abs/2307.01848) find
  108. Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, and Haibin Yan. 2024. Embodied instruction following in unknown environments. arXiv preprint arXiv:2406.11818. — [arXiv:2406.11818](https://arxiv.org/abs/2406.11818) find
  109. Guowei Xu, Peng Jin, Ziang Wu, Hao Li, Yibing Song, Lichao Sun, and Li Yuan. 2024. Llava-cot: Let vision language models reason step-by-step. arXiv preprint arXiv:2411.10440. find
  110. Haotian Xu, Xing Wu, Weinong Wang, Zhongzhi Li, Da Zheng, Boyuan Chen, Yi Hu, Shijia Kang, Jiaming Ji, Yingying Zhang, and 1 others. 2025. Redstar: Does scaling long-cot data unlock better slow-reasoning systems? arXiv preprint arXiv:2501.11284. find
  111. Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, and Tong Zhang. 2025a. Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. Prep… — [arXiv:2502.09560](https://arxiv.org/abs/2502.09560) find
  112. Llama-berry: Pairwise optimization for o1-like olympiad-level mathematical reasoning. arXiv preprint arXiv:2410.02884. find
  113. Jiazhao Zhang, Anqi Li, Yunpeng Qi, Minghan Li, Jiahang Liu, Shaoan Wang, Haoran Liu, Gengze Zhou, Yuze Wu, Xingxing Li, Yuxin Fan, Wenjun Li, Zhibo Chen, Fei Gao, Qi Wu, Zhizheng Zhang, and He Wang. 2025a. Embodied navigation foundation model. Preprint, arXiv:2509.12129. — [arXiv:2509.12129](https://arxiv.org/abs/2509.12129) find
  114. Jiazhao Zhang, Kunyu Wang, Shaoan Wang, Minghan Li, Haoran Liu, Songlin Wei, Zhongyuan Wang, Zhizheng Zhang, and He Wang. 2024b. Uni-navid: A video-based vision-language-action model for unifying embodied navigation tasks. arXiv preprint arXiv:2412.06224. — [arXiv:2412.06224](https://arxiv.org/abs/2412.06224) find
  115. Jiazhao Zhang, Kunyu Wang, Rongtao Xu, Gengze Zhou, Yicong Hong, Xiaomeng Fang, Qi Wu, Zhizheng Zhang, and He Wang. 2024c. Navid: Video-based vlm plans the next step for vision-and-language navigation. arXiv preprint arXiv:2402.15852. — [arXiv:2402.15852](https://arxiv.org/abs/2402.15852) find
  116. Yi Yang, Xiaoxuan He, Hongkun Pan, Xiyan Jiang, Yan Deng, Xingtao Yang, Haoyu Lu, Dacheng Yin, Fengyun Rao, Minfeng Zhu, and 1 others. 2025b. R1-onevision: Advancing generalized multimodal reasoning through cross-modal formalization. arXiv preprint arXiv:2503.10615. find
  117. Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang, Haoxiang Fu, Xinyu Zheng, Pengwei Wang, Zhongyuan Wang, Wenbo Ding, and Shanghang Zhang. 2025b. nava Θ3: Understanding any instruction, navigating anywhere, finding anything. arXiv preprint arXiv:2508.04598. — [arXiv:2508.04598](https://arxiv.org/abs/2508.04598) find
  118. Huanjin Yao, Jiaxing Huang, Wenhao Wu, Jingyi Zhang, Yibo Wang, Shunyu Liu, Yingjie Wang, Yuxin Song, Haocheng Feng, Li Shen, and 1 others. 2024. Mulberry: Empowering mllm with o1-like reasoning and reflection via collective monte carlo tree search. arXiv preprint arXiv:2412.18319. — [arXiv:2412.18319](https://arxiv.org/abs/2412.18319) find
  119. Ruohong Zhang, Bowen Zhang, Yanghao Li, Haotian Zhang, Zhiqing Sun, Zhe Gan, Yinfei Yang, Ruoming Pang, and Yiming Yang. 2024d. Improve vision language model chain-of-thought reasoning. arXiv preprint arXiv:2410.16198.
  120. Sriram Yenamandra, Arun Ramachandran, Karmesh Yadav, Austin Wang, Mukul Khanna, Theophile Gervet, Tsung-Yen Yang, Vidhi Jain, Alexander William Clegg, John Turner, and 1 others. 2023. Homer-obot: Open-vocabulary mobile manipulation. arXiv preprint arXiv:2306.11565. — [arXiv:2306.11565](https://arxiv.org/abs/2306.11565) find
  121. Naoki Yokoyama, Ram Ramrakhya, Abhishek Das, Dhruv Batra, and Sehoon Ha. 2024. Hm3d-ovon: A dataset and benchmark for open-vocabulary object goal navigation. In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5543–5550. IEEE. find
  122. Michał Zawalski, William Chen, Karl Pertsch, Oier Mees, Chelsea Finn, and Sergey Levine. 2024. Robotic control via embodied chain-of-thought reasoning. arXiv preprint arXiv:2407.08693. — [arXiv:2407.08693](https://arxiv.org/abs/2407.08693) find
  123. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. 2022. Star: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems, 35:15476–15488.
  124. Di Zhang, Jianbo Wu, Jingdi Lei, Tong Che, Jiatong Li, Tong Xie, Xiaoshui Huang, Shufei Zhang, Marco Pavone, Yuqiang Li, and 1 others. 2024a. find
  125. Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, and Weiming Lu. 2024e. Self-contrast: Better reflection through inconsistent solving perspectives. arXiv preprint arXiv:2401.02009.
  126. Wenqi Zhang, Ke Tang, Hai Wu, Mengna Wang, Yongliang Shen, Guiyang Hou, Zeqi Tan, Peng Li, Yueting Zhuang, and Weiming Lu. 2024f. Agent-pro: Learning to evolve via policy-level reflection and optimization. arXiv preprint arXiv:2402.17574.
  127. Wenqi Zhang, Hang Zhang, Xin Li, Jiashuo Sun, Yongliang Shen, Weiming Lu, Deli Zhao, Yueting Zhuang, and Lidong Bing. 2025c. 2.5 years in class: A multimodal textbook for vision-language pretraining. arXiv preprint arXiv:2501.00958. — [arXiv:2501.00958](https://arxiv.org/abs/2501.00958) find
  128. Yichi Zhang and Joyce Chai. 2021. Hierarchical task learning from language instructions with unified transformers and self-monitoring. arXiv preprint arXiv:2106.03427. find
  129. Yuxiang Zhang, Shangxi Wu, Yuqi Yang, Jiangming Shu, Jinlin Xiao, Chao Kong, and Jitao Sang. 2024g. o1-coder: an o1 replication for coding. arXiv preprint arXiv:2412.00154. — [arXiv:2412.00154](https://arxiv.org/abs/2412.00154) find
  130. Yu Zhao, Huifeng Yin, Bo Zeng, Hao Wang, Tianqi Shi, Chenyang Lyu, Longyue Wang, Weihua Luo, and Kaifu Zhang. 2024a. Marco-o1: Towards open reasoning models for open-ended solutions. arXiv preprint arXiv:2411.14405. find
  131. Zhonghan Zhao, Wenhao Chai, Xuan Wang, Boyi Li, Shengyu Hao, Shidong Cao, Tian Ye, and Gaoang Wang. 2024b. See and think: Embodied agent in virtual environment. In European Conference on Computer Vision, pages 187–204. Springer. find
  132. Duo Zheng, Shijia Huang, Lin Zhao, Yiwu Zhong, and Liwei Wang. 2024. Towards learning a generalist model for embodied navigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13624–13634. find
  133. Gengze Zhou, Yicong Hong, Zun Wang, Xin Eric Wang, and Qi Wu. 2024a. Navgpt-2: Unleashing navigational reasoning capability for large vision-language models. In European Conference on Computer Vision, pages 260–278. Springer. find
  134. Gengze Zhou, Yicong Hong, and Qi Wu. 2024b. Navgpt: Explicit reasoning in vision-and-language navigation with large language models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 7641–7649. find
  135. Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J Lim, Abhinav Gupta, Li Fei-Fei, and Ali Farhadi. 2017. Target-driven visual navigation in indoor scenes using deep reinforcement learning. In 2017 IEEE international conference on robotics and automation (ICRA), pages 3357–3364. IEEE. find
  136. Ziyu Zhu, Xilin Wang, Yixuan Li, Zhuofan Zhang, Xiaojian Ma, Yixin Chen, Baoxiong Jia, Wei Liang, Qian Yu, Zhidong Deng, and 1 others. 2025. Move to understand a 3d scene: Bridging visual grounding and exploration for efficient and versatile embodied navigation. arXiv preprint arXiv:2507.04047. — [arXiv:2507.04047](https://arxiv.org/abs/2507.04047) find
  137. Filippo Ziliotto, Tommaso Campari, Luciano Serafini, and Lamberto Ballan. 2024. Tango: Training-free embodied ai agents for open-world tasks. arXiv preprint arXiv:2412.10402. — [arXiv:2412.10402](https://arxiv.org/abs/2412.10402) find
  138. Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks Experiment Details find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-embodied-reasoner-synergizing-visual-search/