While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored. Visual Sudoku puzzles pose a representative challenge, requiring multi-step deductive reasoning over both local constraints and global dependency c...
Si-Da Li, Yuan-Xin Liu, Lin-Li Yao et al.· Conference on Empirical Meth...· 0 citations
The MiMo-V2.6 series is introduced, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute by building infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inf...
Xiao-Zhen Qiao, Zi-Yue Hua, Zi-Rui Ou et al.· 10 citations
Reinforcement learning (RL) for code agents often uses executable tests to provide binary rewards. With these rewards, Group Relative Policy Optimization (GRPO) assigns identical advantages to test-passing trajectories within each rollout group, overlooking differences in implementation quality and adherence to task re...
Jin-Hao Dong, Liang Zhao, Zi-Hao Yue et al.· 1 citation
Training capable coding agents via reinforcement learning (RL) requires diverse tasks with reliable verifiers. Open-source codebases offer a rich source of such tasks, while existing methods typically rely on development artifacts such as issues and commits, limiting the range of tasks that can be extracted. To better...
Bo-Wen Ye, Lei Li, Shi-Cheng Li et al.· 0 citations
This work studies ViT attention heads and finds they differentiate into object- and background-specialist roles, a pattern most pronounced under full attention, and proposes SHS-Index to quantify this specialization, showing that it distinguishes full-attention from chunk-window ViTs, and finds that it strongly tracks...
Chenyu He, Lei Li, Shi-Cheng Li et al.· 0 citations
The Lit2Test benchmark centers on a six-field contract organized around a falsifying outcome, so that every proposal precommits the observation that would prove it wrong, making its quality decidable in the first place rather than merely arguable.
Zi-Yue Wang, Aomufei Yuan, Yi-Ran Yao et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.