← Back to all news
arXiv AI By Sida Li, Yuanxin Liu, Linli Yao, Shicheng Li, Xu Sun, Haoli Bai, Xiaohui Li

AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning

Read the original on arXiv AI →

AdaC-GRPO introduces an adaptive curriculum learning framework for mastering long-horizon visual Sudoku puzzles, a multimodal task that challenges large language models with multi-step deductive reasoning. The authors present FG-Sudoku, a fine-grained benchmark that categorizes puzzles by grid size and required deductive steps, revealing that frontier multimodal large language models (MLLMs) struggle with complex long-range dependencies. AdaC-GRPO dynamically constructs training batches by tracking the model’s Zone of Proximal Development through online rollout accuracy, enabling Qwen2.5-VL-7B to close a significant portion of the accuracy gap to Gemini-2.5-Pro and demonstrating generalizability across other models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jun 9

CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning

arXiv:2509. 25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems.

By Shijie Zhang, Zheng Xiao, Shiyu Liu, Guohao Sun, Kevin Zhang, Xiang Guo, Rujun Guo, Shaoyu Liu, Wangxiao Zhao, Guanjun Jiang
llmsreinforcement-learningbenchmarks
More like this →
arXiv AI
Oct 2

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States

The paper introduces POISE, a reinforcement learning algorithm that uses a model’s internal states as a value estimator to reduce variance in reinforcement learning with verifiable rewards (RLVR). By employing a lightweight probe that reads internal signals during the forward pass, POISE predicts baselines online and uses a cross‑rollout construction to keep gradients unbiased. Experiments on Qwen3‑4B and OLMo3‑7B‑Instruct‑DPO across six domains show POISE outperforms existing RLVR baselines, offering more stable training and a value model that generalizes across tasks and scales with the policy.

By Yunho Choi, Jongwon Lim, Woojin Ahn, Minjae Oh, Jeonghoon Shim, Yohan Jo
llmsreinforcement-learning
More like this →