**SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks** > Self-play

**SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks**

> Self-play can train language models without external supervision. However, existing methods require rule-checkable answers, leaving open-ended tasks dependent on curated prompts or frontier-model judges. We introduce SCOPE, a data-free self-play framework for open-ended tasks that co-evolves two policies: a Challenger that generates document-grounded tasks, and a Solver that answers them through multi-turn retrieval....

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：ai-models
- **发布时间**：2026-06-01 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2605.31433)