跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 7 天前AI 評分40

RAPO:長鏈多模態推理中的傳播感知視覺保留反思錨點

Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning

AI 導讀

RAPO 透過識別高熵推理位置作為稀疏反思錨點,並以 chain-masked KL 目標訓練策略在後續推理中保留視覺影響。在 Qwen3-VL-2B-Instruct 上,RAPO 將六項基準的平均 mean@8 accuracy 從 GRPO 的 40.79 提升至 43.01。標準推理時無須額外重新注入視覺資訊或選擇錨點。

正文

RAPO: Keeping Visual Evidence in the Loop during Long-Chain Reasoning

Excited to share our NeurIPS 2026 paper, Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning!

As multimodal reasoning chains grow longer, models can gradually lose their dependence on visual evidence and rely increasingly on generated text.

We introduce Reflection-Anchor Policy Optimization (RAPO), which identifies high-entropy reasoning positions as sparse reflection anchors and trains the policy to preserve visual influence in downstream reasoning through a chain-masked KL objective.

Key highlights:

  • Principled motivation: An information-theoretic analysis of local branching and downstream visual propagation.
  • Propagation-aware optimization: Strengthening visual dependence beyond individual reasoning steps.
  • Stronger performance: On Qwen3-VL-2B-Instruct, RAPO improves the six-benchmark average from 40.79 (GRPO) to 43.01 (mean@8 accuracy).
  • Standard inference: No additional visual re-injection or anchor selection during decoding.

Paper: https://arxiv.org/abs/2605.09614

Project: https://coder-gx.github.io/RAPO/

GitHub: https://github.com/coder-gx/RAPO

We welcome feedback and discussion!

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co