@inproceedings{guo-etal-2026-counteracting,
    title = "Counteracting the Matthew Effect in Self-Improvement of {LVLM}s through Head-Tail Re-balancing",
    author = "Guo, Xin  and
      Xi, Zhiheng  and
      Ding, Yiwen  and
      Zhai, Yitao  and
      Shi, Xiaowei  and
      Cai, Xunliang  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1010/",
    pages = "22104--22121",
    ISBN = "979-8-89176-390-6",
    abstract = "Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision{--}language models (LVLMs), where models explore and learn from successful trajectories iteratively. However, we identify a critical imbalance during this process: the model readily generates high-quality trajectories for simple queries (i.e., head data) but struggles with complex ones (i.e., tail data). This bias drives the optimization to disproportionately prioritize simple reasoning skills, while inhibiting the acquisition of complex capabilities. As iterations progress, this imbalance becomes more acute{---}a dynamic we term the ``Matthew effect'', ultimately stalling performance gains. To mitigate this, we approach head-tail re-balance during the exploration-and-learning process from two perspectives: distribution-reshaping and trajectory-resampling. Extensive experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models across visual reasoning tasks demonstrate that our methods consistently improve visual reasoning capabilities, outperforming vanilla self-improvement baselines by an average of 3.86 points."
}