{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:05Z","timestamp":1788894425152,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37044-0_3","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:20:26Z","timestamp":1788891626000},"page":"37-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Advantage Estimation with\u00a0Unified Critic for\u00a0VLM Agentic Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Wenxuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donggang","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqian","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivan","family":"Viola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"3_CR1","unstructured":"Anthropic: Claude Sonnet 4.5 system card (2025). https:\/\/www.anthropic.com\/claude-sonnet-4-5-system-card. Accessed 1 Jul 2026"},{"key":"3_CR2","unstructured":"Azzolini, A., et al.: Cosmos-Reason1: from physical common sense to embodied reasoning. arXiv preprint arXiv:2503.15558 (2025)"},{"key":"3_CR3","unstructured":"Bai, H., Zhou, Y., Li, L.E., Levine, S., Kumar, A.: Digi-Q: learning VLM Q-value functions for training device-control agents. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Bai, H., et al.: DigiRL: training in-the-wild device-control agents with autonomous reinforcement learning. Adv. Neural. Inf. Process. Syst. 37, 12461\u201312495 (2024)","DOI":"10.52202\/079017-0397"},{"key":"3_CR5","unstructured":"Bai, S., et al.: Qwen3-VL technical report (2025)"},{"key":"3_CR6","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report (2025)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chen, J., Guo, H., Yi, K., Li, B., Elhoseiny, M.: VisualGPT: data-efficient adaptation of pretrained language models for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18030\u201318040 (2022)","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"3_CR8","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"3_CR9","unstructured":"Chen, K., et al.: Reinforcement learning for long-horizon interactive LLM agents. arXiv preprint arXiv:2502.01600 (2025)"},{"key":"3_CR10","unstructured":"Chu, T., et al.: SFT memorizes, RL generalizes: a comparative study of foundation model post-training. In: Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0267, pp. 10818\u201310838. PMLR (2025)"},{"key":"3_CR11","unstructured":"Faldor, M., Zhang, J., Cully, A., Clune, J.: OMNI-EPIC: open-endedness via models of human notions of interestingness with environments programmed in code. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"3_CR12","doi-asserted-by":"publisher","first-page":"18343","DOI":"10.52202\/068431-1333","volume":"35","author":"L Fan","year":"2022","unstructured":"Fan, L., et al.: MineDojo: building open-ended embodied agents with internet-scale knowledge. Adv. Neural. Inf. Process. Syst. 35, 18343\u201318362 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Feng, L., Xue, Z., Liu, T., An, B.: Group-in-group policy optimization for LLM agent training. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-1544"},{"key":"3_CR14","unstructured":"Google DeepMind: Gemini 2.5 pro model card (2025). https:\/\/storage.googleapis.com\/deepmind-media\/Model-Cards\/Gemini-2-5-Pro-Model-Card.pdf. Updated: 27 Jun 2025. Accessed 1 Jul 2026"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Guo, D., et al.: DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645, 633\u2013638 (2025). https:\/\/doi.org\/10.1038\/s41586-025-09422-z","DOI":"10.1038\/s41586-025-09422-z"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Hiranaka, A., et al.: Primitive skill-based robot learning from human evaluative feedback. In: 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 7817\u20137824. IEEE (2023)","DOI":"10.1109\/IROS55552.2023.10341912"},{"key":"3_CR17","unstructured":"Jin, C., et al.: AlphaBlock: embodied finetuning for vision-language reasoning in robot manipulation. arXiv preprint arXiv:2305.18898 (2023)"},{"key":"3_CR18","unstructured":"Klissarov, M., Hjelm, R.D., Toshev, A.T., Mazoure, B.: On the modeling capabilities of large language models for sequential decision making. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"3_CR19","unstructured":"Kolve, E., et\u00a0al.: AI2-THOR: an interactive 3D environment for Visual AI. arXiv preprint arXiv:1712.05474 (2017)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)","DOI":"10.52202\/075280-1516"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., Bai, C., Lyu, J., Sun, S., Du, Y., Li, X.: VLP: vision-language preference learning for embodied manipulation. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 28428\u201328444. Association for Computational Linguistics (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1444"},{"key":"3_CR22","unstructured":"Liu, Z., et al.: Visual agentic reinforcement fine-tuning. arXiv arXiv:2505.14246 (2025)"},{"key":"3_CR23","unstructured":"Lu, M., et al.: Scaling agentic reinforcement learning for tool-integrated reasoning in VLMs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26518\u201326529 (2026)"},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"27529","DOI":"10.52202\/079017-0865","volume":"37","author":"P Mazzaglia","year":"2024","unstructured":"Mazzaglia, P., Verbelen, T., Dhoedt, B., Courville, A., Rajeswar, S.: GenRL: multimodal-foundation world models for generalization in embodied agents. Adv. Neural. Inf. Process. Syst. 37, 27529\u201327555 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., Liu, H., Zhu, Y.: Augmenting reinforcement learning with behavior primitives for diverse manipulation tasks. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 7477\u20137484. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812140"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"key":"3_CR27","unstructured":"Radford, A., et al..: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning, 18\u201324 July 2021. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"75942","DOI":"10.52202\/079017-2418","volume":"37","author":"G Sarch","year":"2024","unstructured":"Sarch, G., Jang, L., Tarr, M., Cohen, W.W., Marino, K., Fragkiadaki, K.: VLM agents generate their own memories: distilling experience into embodied programs of thought. Adv. Neural. Inf. Process. Syst. 37, 75942\u201375985 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR29","unstructured":"Schmidhuber, J.: Towards compositional learning with dynamic neural networks. Inst. f\u00fcr Informatik (1990)"},{"key":"3_CR30","unstructured":"Schmidhuber, J.: Learning to generate sub-goals for action sequences. In: Artificial Neural Networks, pp. 967\u2013972 (1991)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J., Wahnsiedler, R.: Planning simple trajectories using neural subgoal generators. In: Proceedings of the 2nd International Conference on Simulation of Adaptive Behavior, pp. 196\u2013202 (1992)","DOI":"10.7551\/mitpress\/3116.003.0027"},{"key":"3_CR32","unstructured":"Schrader, M.P.B.: gym-sokoban (2018). https:\/\/github.com\/mpSchrader\/gym-sokoban. Accessed 1 Jul 2026"},{"key":"3_CR33","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: International Conference on Learning Representations (2016)"},{"key":"3_CR34","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"3_CR35","unstructured":"Shen, H., et al..: VLM-R1: a stable and generalizable R1-style large vision-language model. arXiv preprint arXiv:2504.07615 (2025)"},{"key":"3_CR36","unstructured":"Shen, W., Hu, J., Zhao, P., He, X., Chen, L.: Advanced tricks for training large language models with proximal policy optimization (2024). https:\/\/swtheking.notion.site\/eb7b2d1891f44b3a84e7396d19d39e6f?v=01bcb084210149488d730064cbabc99f&pvs=74, Notion Blog. Accessed 28 Jun 2026"},{"key":"3_CR37","unstructured":"Sheng, G., et al.: HybridFlow: a flexible and efficient RLHF framework. arXiv preprint arXiv: 2409.19256 (2024)"},{"key":"3_CR38","unstructured":"Singh, A., et\u00a0al.: OpenAI GPT-5 system card (2025). https:\/\/openai.com\/index\/gpt-5-system-card\/. Accessed 1 Jul 2026"},{"key":"3_CR39","unstructured":"Srivastava, S., et al.: ROSETTA: constructing code-based reward from unconstrained language preference. In: Workshop on Continual Robot Learning from Humans (2025)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Tang, G., Rajkumar, S., Zhou, Y., Walke, H.R., Levine, S., Fang, K.: KALIE: fine-tuning vision-language models for open-world manipulation without robot data. In: 2025 IEEE International Conference on Robotics and Automation (ICRA), pp. 9507\u20139515. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11128156"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Tao, S., et\u00a0al.: ManiSkill3: GPU parallelized robotics simulation and rendering for generalizable embodied AI. In: Robotics: Science and Systems (2025)","DOI":"10.15607\/RSS.2025.XXI.021"},{"key":"3_CR42","unstructured":"Google Team, et al.: Gemma 3 technical report (2025)"},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Towers, M., et\u00a0al.: Gymnasium: a standard interface for reinforcement learning environments. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2025)","DOI":"10.52202\/085713-4916"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Wang, K., et\u00a0al.: VAGEN: reinforcing world model reasoning for multi-turn VLM agents. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-5754"},{"key":"3_CR45","unstructured":"Wang, Z., et\u00a0al.: RAGEN: understanding self-evolution in LLM agents via multi-turn reinforcement learning. arXiv preprint arXiv:2504.20073 (2025)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Wei, T., Yang, Y., Xing, J., Shi, Y., Lu, Z., Ye, D.: GTR: guided thought reinforcement prevents thought collapse in RL-based VLM agent training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18855\u201318865 (2025)","DOI":"10.1109\/ICCV51701.2025.01752"},{"key":"3_CR47","unstructured":"Wei, T., et al.: GTR-turbo: merged checkpoint is secretly a free teacher for agentic VLM training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26476\u201326486 (2026)"},{"key":"3_CR48","doi-asserted-by":"publisher","unstructured":"Yang, J., Ding, R., Brown, E., Qi, X., Xie, S.: V-IRL: grounding virtual intelligence in real life. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, ECCV 2024. LNCS, vol. 15103, pp. 36\u201355. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72995-9_3","DOI":"10.1007\/978-3-031-72995-9_3"},{"key":"3_CR49","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Octopus: embodied vision-language programmer from environmental feedback. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15059, pp. 20\u201338. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_2","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"3_CR50","unstructured":"Yang, R., et\u00a0al.: EmbodiedBench: comprehensive benchmarking multi-modal large language models for vision-driven embodied agents. In: Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0267, pp. 70576\u201370631. PMLR (2025)"},{"key":"3_CR51","unstructured":"Yang, S., et al.: Learning interactive real-world simulators. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"3_CR52","doi-asserted-by":"publisher","first-page":"110935","DOI":"10.52202\/079017-3522","volume":"37","author":"S Zhai","year":"2024","unstructured":"Zhai, S., et al.: Fine-tuning large vision-language models as decision-making agents via reinforcement learning. Adv. Neural. Inf. Process. Syst. 37, 110935\u2013110971 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR53","unstructured":"Zhang, L., et\u00a0al.: Mem2Ego: empowering vision-language models with global-to-ego memory for long-horizon embodied navigation. In: Workshop on Foundation Models Meet Embodied Agents at CVPR 2025 (2025)"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, E., et al.: Chain-of-imagination for reliable instruction following in decision making. In: 2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 10010\u201310017. IEEE (2025)","DOI":"10.1109\/IROS60139.2025.11246335"},{"key":"3_CR55","unstructured":"Zhou, Y., et al.: Proposer-agent-evaluator (PAE): autonomous skill discovery for foundation model internet agents. In: Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0267, pp. 79490\u201379528. PMLR (2025)"},{"key":"3_CR56","unstructured":"Zhou, Y., Zanette, A.: ArCHer: training language model agents via hierarchical multi-turn RL. In: Proceedings of the 41st International Conference on Machine Learning, pp. 62178\u201362209 (2024)"},{"key":"3_CR57","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: International Conference on Learning Representations (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:20:36Z","timestamp":1788891636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}