… The compiled configuration set further serves as a reusable optimization artifact, enabling flexible deployment under varying runtime preferences and supporting downstream selection or routing. …
… The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating th… …
Papers arxiv:2605.12995 F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking Published on May 13 Submitted by Rohan Surana on May 14 McAuley-Lab Authors: Rohan Surana , , , , , , , , , , , Abstract A unified framework combines candidate generation and r… …
Papers arxiv:2605.06139 Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex Published on May 7 Submitted by Yun Qu on May 11 Tencent Hunyuan Authors: Yun Qu , , , , , , , , , , , , , Abstract Group-based policy gradient methods in reinforcement learning w… …
Papers arxiv:2604.24953 ViPO: Visual Preference Optimization at Scale Published on Apr 29 Submitted by Ming Li on May 1 Authors: Ming Li , , , , , Abstract Scaling visual preference optimization requires addressing noisy datasets through adaptive Poly-DPO methodology and high-quality data construct… …
Papers arxiv:2605.09932 FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning Published on May 11 Submitted by JarvisPei on May 13 Authors: , , , , , Abstract Training framework FocuSFT improves long-context language model performance by addressing attention allocation issues th… …
Papers arxiv:2605.12481 ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents Published on May 12 Submitted by XuHao Hu on May 13 TongyiLab Authors: Xuhao Hu , , Haiyang Xu , , Jingyi Yang , , , , Abstract ToolCUA is an end-to-end agent that learns optimal GUI-tool path selec… …
Papers arxiv:2605.10341 PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents Published on May 11 Submitted by Cheng Tan on May 12 OpenDataLab Authors: , , , , , Siyuan Li , , , Cheng Tan Abstract Visual typesetting optimization addresses the gap between compilable LaTeX do… …
… This yields an optimization mechanism that modulates the geometry of weight matrices while keeping their spectral norm fixed. …
Papers arxiv:2605.04077 Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO Published on Apr 14 Submitted by zhiyuan zeng on May 8 OpenMOSS Authors: , , , , , , , , , , Abstract Balanced Aggregation improves reinforcement learning with verifiable rewards by addressing optimizati… …