…AI-generated summary Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority voting (MV), a test-time technique called…
Papers arxiv:2605.07396 Rubric-based On-policy Distillation Published on May 8 Submitted by zhepeihong on May 11 Authors: , Zhepei Hong , , , , , Dan Zhang , , , Abstract Rubric-based on-policy distillation achieves improved…
…Yuanzhi Wang , , , , , , , Abstract Implicit Preference Alignment (IPA) addresses hand motion generation challenges through data-efficient post-training that eliminates need for paired preference data while using hand-aware local optimization for improved…
…View arXiv page View PDF Add to collection Community code was not released? This is an automated message from the Librarian Bot . I found the following papers similar to this paper. The…
…the-art performance and significantly improves alignment with complex human preferences, without requiring additional human annotation or explicit reward models during training. We will release our code and models at: https://github…
…Our code is available at https://github.com/hongruhou89/ProRL. View arXiv page View PDF GitHub 40 Add to collection Community Standard policy gradients are fundamentally broken for proactive recommendation. ProRL fixes…
…Through a closed-loop run--verify--reflect process , the framework jointly improves decomposition and execution over time via persistent, human-readable external memory , with self-evolving updates to each single-agent. During…
…On LoCoMo, EvolveMem outperforms the strongest baseline by 25.7% relative and achieves a 78.0% relative improvement over the minimal baseline. On MemBench, EvolveMem exceeds the strongest baseline by 18.9…
…Is there a source code available? Get this paper in your agent: hf papers read 2605.05806 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash…
…Furthermore, improvements from model scaling quickly saturate, strong general reasoning does not reliably translate to creative affordance discovery, and common inference-time strategies such as Chain-of-Thought yield limited gains. These…