Elamur Research⌕
☰
home / papers / 2025 / Progressive Multimodal Reasoning via Active Retrieval

Progressive Multimodal Reasoning via Active Retrieval

Paper · 2025 · Guanting Dong, Chenghao Zhang, Mengjie Deng et al.

Summary

The paper addresses the difficulty multimodal large language models (MLLMs) have with multi-step reasoning. MCTS-based step annotation works well for text-only LLMs, but in the multimodal case its expansion phase depends on the model's own knowledge. Misalignment between image and text inputs makes that knowledge unreliable. The authors propose AR-MCTS, which combines Monte Carlo Tree Search with Active Retrieval. At each expansion step, instead of relying on beam search, the system pulls problem-solving insights from a hybrid-modal corpus. That corpus mixes Wikipedia, COIG and text-only and multimodal math datasets, and a knowledge concept filtering step removes noisy retrieved items. The MCTS rollouts produce step-level annotations without human labeling. These annotations are used to train a process reward model (PRM) in two curriculum stages, step-wise DPO followed by SFT, so it can verify reasoning step by step. Across three complex multimodal reasoning benchmarks, AR-MCTS improves results for several MLLMs and yields more diverse and more accurate candidate solutions. This suggests retrieval-guided search is a scalable, low-cost route to reliable multimodal reasoning verification.

Key points

  • Retrieval corpus:
    • General knowledge comes from Wikipedia en-US (15B, ~76%), Wikipedia zh-CN (4.7B, ~23.9%) and COIG (178K).
    • Math knowledge comes from GSM8K (8,792), MATH (12,500), MathVista (6,141), MathVerse (2,612), MathVision (3,040) and We-Math (1,740).
  • Ablation on MathVista:
    • Dropping the PRM lowers accuracy by 3.1%, and dropping active retrieval lowers it by 2.2%.
    • Knowledge concept filtering gives consistent gains.
  • Scaling (1 to 32 sampled paths):
    • AR-MCTS stays ahead of ORM and self-consistency, and the margin grows with more samples.
    • Self-consistency becomes unstable on We-Math beyond 16 samples.
  • Diversity:
    • Setup: 250 MathVista problems × 4 solutions, embedded with BGE-M3, reduced with PCA and clustered with DBSCAN.
    • Result: AR-MCTS solutions form 46 clusters versus 38 for beam search.
  • Sampling accuracy: With Qwen2-VL, AR-MCTS raises the share of questions with at least one correct candidate compared with beam search.

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

🎓Renmin University of ChinaBeijing · China114 works · 16,118 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputer Vision and Pattern Recognition · 2,869 worksInformation Systems · 1,437 works

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1,426 worksVision & language · 657 worksInformation retrieval & search · 473 works

Cite

Cite as Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou and Ji-Rong Wen. 2025. Progressive Multimodal Reasoning via Active Retrieval. Proceedings of the 63rd 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/v1/2025.acl-long.180

@inproceedings{dong2025progressive,
  title = {{Progressive Multimodal Reasoning via Active Retrieval}},
  author = {Guanting Dong, Chenghao Zhang, Mengjie Deng, Yutao Zhu, Zhicheng Dou and Ji-Rong Wen},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.180},
  url = {https://doi.org/10.18653/v1/2025.acl-long.180}
}

References

113 references, 58 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-rag: Learning to retrieve, generate, and critique through self-reflection. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
  2. Giusepppe Attardi. 2015. Wikiextractor. https://github.com/attardi/wikiextractor. ↗
  3. Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. Preprint, arXiv:2308.12966.
  4. Cameron Browne, Edward Jack Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez Liebana, Spyridon Samothrakis, and Simon Colton. 2012. A survey of monte carlo tree search methods. IEEE Trans. Comput. Intell. AI Games, 4(1):1–43. find
  5. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, Aijia Guo, Qipeng Guo, Conghui He, Yingfan Hu, Ting Huang, Tao Jiang, Penglong Jiao, Zhenjia… — InternLM2 Technical Report
  6. Guoxin Chen, Minpeng Liao, Chengxi Li, and Kai Fan. 2024a. Alphamath almost zero: process supervision without process. CoRR, abs/2405.03553.
  7. Guoxin Chen, Minpeng Liao, Chengxi Li, and Kai Fan. 2024b. Step-level value preference optimization for mathematical reasoning. CoRR, abs/2406.10858. find
  8. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024c. BGE m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. CoRR, abs/2402.03216.
  9. Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W. Cohen. 2023a. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. find
  10. Trans. Mach. Learn. Res., 2023. find
  11. Zhe Chen, Weiyun Wang, Hao Tian, Shenglong Ye, Zhangwei Gao, Erfei Cui, Wenwen Tong, Kongzhi Hu, Jiapeng Luo, Zheng Ma, Ji Ma, Jiaqi Wang, Xiaoyi Dong, Hang Yan, Hewei Guo, Conghui He, Botian Shi, Zhenjiang Jin, Chao Xu, Bin Wang, Xingjian Wei, Wei Li, Wenjian Zhang, Bo Zhang, Pinlong Cai, Licheng W… — How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
  12. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023b. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. arXiv preprint arXiv:2312.14…
  13. Yiruo Cheng, Kelong Mao, Ziliang Zhao, Guanting Dong, Hongjin Qian, Yongkang Wu, Tetsuya Sakai, Ji-Rong Wen, and Zhicheng Dou. 2024. CORAL: benchmarking multi-turn conversational retrieval-augmentation generation. CoRR, abs/2410.23090. — [arXiv:2410.23090](https://arxiv.org/abs/2410.23090) find
  14. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021a. Training verifiers to solve math word problems. CoRR, abs/2110.14168.
  15. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021b. Training verifiers to solve math word problems. CoRR, abs/2110.14168.
  16. Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. CoRR.
  17. Guanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin, Hongjin Qian, Yutao Zhu, Hangyu Mao, Guorui Zhou, Zhicheng Dou, and Ji-Rong Wen. 2025. Tool-star: Empowering llm-brained multi-tool reasoner via reinforcement learning. Preprint, arXiv:2505.16410. — [arXiv:2505.16410](https://arxiv.org/abs/2505.16410) find
  18. Guanting Dong, Rumei Li, Sirui Wang, Yupeng Zhang, Yunsen Xian, and Weiran Xu. 2023. Bridging the kb-text gap: Leveraging structured knowledge-aware pre-training for KBQA. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United K… find
  19. Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, and Jingren Zhou. 2024a. Self-play with execution feedback: Improving instruction-following capabilities of large language models. CoRR, abs/2406.13542. find
  20. Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2024b. How abilities in large language models are affected by supervised fine-tuning data composition. In Proceedings of the 62nd Annual Meeting of the Association for…
  21. Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, and Ji-Rong Wen. 2024c. Understand what LLM needs: Dual preference alignment for retrieval-augmented generation. CoRR, abs/2406.18676. — [arXiv:2406.18676](https://arxiv.org/abs/2406.18676) find
  22. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao, Aston Zhang, Aurélien Rodriguez,… — The Llama 3 Herd of Models
  23. Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96), Portland, Oregon, USA, pages 226– 231.… find
  24. Markus Freitag and Yaser Al-Onaizan. 2017. Beam search strategies for neural machine translation. In Proceedings of the First Workshop on Neural Machine Translation, NMT@ACL 2017, Vancouver, Canada, August 4, 2017, pages 56–60. Association for Computational Linguistics.
  25. Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. PAL: program-aided language models. In International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Researc… find
  26. Zitian Gao, Boye Niu, Xuzheng He, Haotian Xu, Hongzhang Liu, Aiwei Liu, Xuming Hu, and Lijie Wen. 2024. Interpretable contrastive monte carlo tree search reasoning. Preprint, arXiv:2410.01707. — [arXiv:2410.01707](https://arxiv.org/abs/2410.01707) find
  27. Jiayi He, Hehai Lin, Qingyun Wang, Yi Fung, and Heng Ji. 2024. Self-correction is more than refinement: A learning framework for visual and language reasoning tasks. Preprint, arXiv:2410.04055. find
  28. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the MATH dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets an…
  29. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. Unsupervised dense information retrieval with contrastive learning.
  30. Trans. Mach. Learn. Res., 2022. find
  31. Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Qi Ye, and Zhicheng Dou. 2025. Hierarchical document refinement for long-context retrieval-augmented generation. arXiv preprint arXiv:2505.10413.
  32. Jiajie Jin, Yutao Zhu, Xinyu Yang, Chenghao Zhang, and Zhicheng Dou. 2024. Flashrag: A modular toolkit for efficient retrieval-augmented generation research. CoRR, abs/2405.13576. find
  33. Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2021. Billion-scale similarity search with gpus. IEEE Trans. Big Data, 7(3):535–547. find
  34. Andreas Koukounas, Georgios Mastrapas, Michael Günther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Martínez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, and Han Xiao. 2024. Jina CLIP: your CLIP model is also your text retriever. CoRR, abs/… — [arXiv:2405.20204](https://arxiv.org/abs/2405.20204) find
  35. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
  36. Shanglin Lei, Guanting Dong, Xiaoping Wang, Keheng Wang, and Sirui Wang. 2023. Instructerc: Reforming emotion recognition in conversation with a retrieval multi-task llms framework. CoRR, abs/2309.11911. — [arXiv:2309.11911](https://arxiv.org/abs/2309.11911) find
  37. Patrick S. H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Informatio…
  38. Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024a. Llava-onevision: Easy visual task transfer. CoRR, abs/2408.03326.
  39. Chengpeng Li, Guanting Dong, Mingfeng Xue, Ru Peng, Xiang Wang, and Dayiheng Liu. 2024b. Dotamath: Decomposition of thought with code assistance and self-correction for mathematical reasoning. CoRR, abs/2407.04078. — [arXiv:2407.04078](https://arxiv.org/abs/2407.04078) find
  40. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025a. Search-o1: Agentic search-enhanced large reasoning models. CoRR, abs/2501.05366.
  41. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou. 2025b. Webthinker: Empowering large reasoning models with deep research capability. CoRR, abs/2504.21776. find
  42. Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Qi Ye, and Zhicheng Dou. 2024c. Retrollm: Empowering large language models to retrieve fine-grained evidence within generation. arXiv preprint arXiv:2412.11919.
  43. Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. 2023. Making language models better reasoners with step-aware verifier. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canad…
  44. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. Open-Rev…
  45. Su Hyeon Lim, Minkuk Kim, Hyeon Bae Kim, and Seong Tae Kim. 2024. Retrieval-augmented natural language reasoning for explainable visual question answering. CoRR, abs/2408.17006. — [arXiv:2408.17006](https://arxiv.org/abs/2408.17006) find
  46. Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, and Hao Su. 2023. Deductive verification of chain-of-thought reasoning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, L…
  47. Bingshuai Liu, Chenyang Lyu, Zijun Min, Zhanyu Wang, Jinsong Su, and Longyue Wang. 2023a. Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models. CoRR, abs/2312.01714.
  48. Haotian Liu, Chunyuan Li, Yuheng Li, Bo Li, Yuanhan Zhang, Sheng Shen, and Yong Jae Lee. Llava-next: Improved reasoning, ocr, and world knowledge. find
  49. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual instruction tuning. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023.
  50. Jiacheng Liu, Andrew Cohen, Ramakanth Pasunuru, Yejin Choi, Hannaneh Hajishirzi, and Asli Celikyilmaz. 2023c. Making PPO even better: Value-guided monte-carlo tree search decoding. CoRR, abs/2309.15028.
  51. Jingyu Liu, Jiaen Lin, and Yong Liu. 2024. How much can RAG help the reasoning of llm? CoRR, abs/2410.02338.
  52. Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, and Jingren Zhou. 2024a. \#instag: Instruction tagging for analyzing supervised fine-tuning of large language models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, M… find
  53. Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2024b. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. In The Twelfth International Conference on Learning Representations…
  54. Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jian-guang Lou, Chongyang Tao, Xiubo Geng, Qingwei Lin, Shifeng Chen, and Dongmei Zhang. 2023. Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct. CoRR, abs/2308.09583.
  55. Haoran Luo, Haihong E, Zichen Tang, Shiyao Peng, Yikai Guo, Wentai Zhang, Chenghao Ma, Guanting Dong, Meina Song, Wei Lin, Yifan Zhu, and Anh Tuan Luu. 2024a. ChatKBQA: A generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models. In Findings of the… find
  56. Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, and Abhinav Rastogi. 2024b. Improve mathematical reasoning in language models by automated process supervision. CoRR, abs/2406.06592.
  57. Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, and Abhinav Rastogi. 2024c. Improve mathematical reasoning in language models by automated process supervision. CoRR, abs/2406.06592.
  58. Qianli Ma, Haotian Zhou, Tingkai Liu, Jianbo Yuan, Pengfei Liu, Yang You, and Hongxia Yang. 2023. Let’s reward step by step: Step-level reward model as the navigators for reasoning. CoRR, abs/2310.10080. find
  59. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. 2023. Self-refine: Iterative refinement with… find
  60. Ning Miao, Yee Whye Teh, and Tom Rainforth. 2024. Selfcheck: Using llms to zero-shot check their own step-by-step reasoning. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. find
  61. OpenAI, :, Aaron Hurst, Adam Lerer, Adam P. Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, Aleksander M adry, Alex Baker-Whitcomb, Alex Beutel, Alex Borzunov, Alex Carney, Alex Chow, Alex Kirillov, Alex Nichol, Alex Paino, Alex Renzin, Alex… — GPT-4o System Card
  62. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. 2023a. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing S…
  63. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. 2023b. Direct preference optimization: Your language model is secretly a reward model. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing S…
  64. OpenAI. 2023a. GPT-4 technical report. abs/2303.08774.
  65. CoRR, OpenAI. 2023b. GPT-4 technical report. abs/2303.08774.
  66. CoRR, Marlou Rasenberg, Asli Özyürek, and Mark Dingemanse. 2020. Alignment in multimodal interaction: An integrative framework. Cogn. Sci., 44(11). find
  67. R OpenAI. 2023c. Gpt-4v (ision) system card. Citekey: gptvision. find
  68. Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. KDD ’20. find
  69. OpenAI. 2024. Hello gpt-4o. find
  70. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. 2022.… — Training language models to follow instructions with human feedback
  71. Martin L. Puterman. 1990. Chapter 8 markov decision processes. In Stochastic Models, volume 2 of Handbooks in Operations Research and Management Science, pages 331–434. Elsevier. find
  72. Runqi Qiao, Qiuna Tan, Guanting Dong, Minhui Wu, Chong Sun, Xiaoshuai Song, Zhuoma Gongque, Shanglin Lei, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Yifan Zhang, Xiao Zong, Yida Xu, Muxi Diao, Zhimin Bao, Chen Li, and Honggang Zhang. 2024. We-math: Does your large multimodal model achieve human-like mat… find
  73. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning transferable visual models from natural language Matthew Renze and Erhan Guven. 2024. Self-reflecti…
  74. Nikhil Sardana, Jacob Portes, Sasha Doubov, and Jonathan Frankle. 2024. Beyond chinchilla-optimal: Accounting for inference in language model scaling laws. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net.
  75. Emre Satir and Hasan Bulut. 2021. Preventing translation quality deterioration caused by beam search decoding in neural machine translation using statistical machine translation. Inf. Sci., 581:791–807. find
  76. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. CoRR, abs/1707.06347. find
  77. Amrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, and Aviral Kumar. 2024a. Rewarding progress: Scaling automated process verifiers for llm reasoning. find
  78. Amrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, and Aviral Kumar. 2024b. Rewarding progress: Scaling automated process verifiers for llm reasoning. arXiv preprint arXiv:2410.08146. find
  79. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. CoRR, abs/2402.03300.
  80. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Richard James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2024. REPLUG: retrieval-augmented black-box language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hum…
  81. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. Scaling LLM test-time compute optimally can be more effective than scaling model parameters. CoRR, abs/2408.03314.
  82. Shezheng Song, Xiaopeng Li, and Shasha Li. 2023. How to bridge the gap between modalities: A comprehensive survey on multimodal large language model. CoRR, abs/2311.07594. — [arXiv:2311.07594](https://arxiv.org/abs/2311.07594) find
  83. Niranjan Srinivas, Andreas Krause, Sham M. Kakade, and Matthias W. Seeger. 2012. Information-theoretic regret bounds for gaussian process optimization in the bandit setting. IEEE Trans. Inf. Theory, 58(5):3250– 3265. find
  84. Zhiqing Sun, Longhui Yu, Yikang Shen, Weiyang Liu, Yiming Yang, Sean Welleck, and Chuang Gan. 2024. Easy-to-hard generalization: Scalable alignment beyond human supervision. CoRR, abs/2403.09472. find
  85. Cheng Tan, Jingxuan Wei, Linzhuang Sun, Zhangyang Gao, Siyuan Li, Bihui Yu, Ruifeng Guo, and Stan Z. Li. 2024. Retrieval meets reasoning: Even high-school textbook knowledge benefits multimodal reasoning. CoRR, abs/2405.20834. — [arXiv:2405.20834](https://arxiv.org/abs/2405.20834) find
  86. Jiejun Tan, Zhicheng Dou, Wen Wang, Mang Wang, Weipeng Chen, and Ji-Rong Wen. 2025. Htmlrag: Html is better than plain text for modeling retrieved knowledge in rag systems. In Proceedings of the ACM on Web Conference 2025, pages 1733–1746. find
  87. Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Haitao Mi, and Dong Yu. 2024. Toward self-improvement of llms via imagination, searching, and criticizing. CoRR, abs/2404.12253. find
  88. Jonathan Uesato, Nate Kushman, Ramana Kumar, Francis Song, Noah Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving math word problems with process- and outcome-based feedback. Preprint, arXiv:2211.14275.
  89. Chaojie Wang, Yanchen Deng, Zhiyi Lv, Zeng Liang, Jujie He, Shuicheng Yan, and Bo An. 2024a. Q*: Improving multi-step reasoning for llms with deliberative planning. CoRR, abs/2406.14283. find
  90. Ke Wang, Junting Pan, Weikang Shi, Zimu Lu, Mingjie Zhan, and Hongsheng Li. 2024b. Measuring multimodal mathematical reasoning with math-vision dataset. CoRR, abs/2402.14804.
  91. Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024c. Math-shepherd: Verify and reinforce llms step-by-step without human annotations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Pape…
  92. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024d. Qwen2-vl: Enhancing vision-language model’s perception of the…
  93. Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024e. Qwen2-vl: Enhancing vision-language model’s perception of the…
  94. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5,…
  95. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processi…
  96. Shijie Xia, Xuefeng Li, Yixin Liu, Tongshuang Wu, and Pengfei Liu. 2024. Evaluating mathematical reasoning beyond accuracy. CoRR, abs/2404.05692.
  97. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Juny… find
  98. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023,… find
  99. Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2024. Making retrieval-augmented language models robust to irrelevant context. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net.
  100. Zichun Yu, Chenyan Xiong, Shi Yu, and Zhiyuan Liu. 2023. Augmentation-adapted retriever improves generalization of language models as generic plug-in. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9… find
  101. Lifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding, Xingyao Wang, Jia Deng, Boji Shan, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, and Maosong Sun. 2024. Advancing LLM reasoning generalists with preference trees. CoRR, abs/2404.02078. find
  102. Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Chuanqi Tan, and Chang Zhou. 2023. Scaling relationship on learning mathematical reasoning with large language models. CoRR, abs/2308.01825.
  103. Chinese open instruction generalist: A preliminary release. CoRR, abs/2304.07987. — [arXiv:2304.07987](https://arxiv.org/abs/2304.07987) find
  104. Renrui Zhang, Dongzhi Jiang, Yichi Zhang, Haokun Lin, Ziyu Guo, Pengshuo Qiu, Aojun Zhou, Pan Lu, Kai-Wei Chang, Peng Gao, and Hongsheng Li. 2024c. Mathverse: Does your multi-modal LLM truly see the diagrams in visual math problems? CoRR, abs/2403.14624.
  105. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. CoRR, abs/2402.19473.
  106. Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, and Yongping Xiong. 2024. VISTA: visualized text embedding for universal multi-modal retrieval. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16,… find
  107. Ren Zhou. 2024. Advanced embedding techniques in multimodal retrieval augmented generation a comprehensive study on cross modal ai applications. Journal of Computing and Electronic Information Management, 13(3):16–22. find
  108. Wenwen Zhuang, Xin Huang, Xiantao Zhang, and Jin Zeng. 2024. Math-puma: Progressive upward multimodal alignment to enhance mathematical reasoning. CoRR, abs/2408.08640. — [arXiv:2408.08640](https://arxiv.org/abs/2408.08640) find
  109. Yi Zong and Xipeng Qiu. 2024. GAOKAO-MM: A chinese human-level benchmark for multimodal models evaluation. In Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and virtual meeting, August 11-16, 2024, pages 8817– 8825. Association for Computational Linguistics.
  110. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah D. Goodman. 2022. Star: Bootstrapping reasoning with reasoning. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022.
  111. Dan Zhang, Sining Zhoubian, Yisong Yue, Yuxiao Dong, and Jie Tang. 2024a. Rest-mcts*: LLM self-training via process reward guided tree search. CoRR, abs/2406.03816.
  112. Di Zhang, Xiaoshui Huang, Dongzhan Zhou, Yuqiang Li, and Wanli Ouyang. 2024b. Accessing GPT-4 level mathematical olympiad solutions via monte carlo tree self-refine with llama-3 8b. CoRR, abs/2406.07394. find
  113. Ge Zhang, Yemin Shi, Ruibo Liu, Ruibin Yuan, Yizhi Li, Siwei Dong, Yu Shu, Zhaoqun Li, Zekun Wang, Chenghua Lin, Wenhao Huang, and Jie Fu. 2023. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/dong-2025-progressive-multimodal-reasoning-active-retrieval/