S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?

  • 类型：arxiv
  • 标识：2608.31100
  • 链接：https://arxiv.org/abs/2608.31100
  • 主分类：evaluation
  • 形态：benchmark
  • 被引：3
  • 被引来源：Semantic Scholar
  • S2被引：3
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：These findings show that recognizing successful actions is insufficient; agents must also transform feedback into executable and transferable policies, and provide a unified framework for diagnosing this process and identifying the bottlenecks that prevent agents from translating interaction experience into reliable self-improvement.
  • OpenAlex ID：W7204896194
  • OpenAlex DOI：10.48550/arxiv.2608.31100
  • DOI：10.48550/arxiv.2608.31100
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://arxiv.org/pdf/2608.31100
  • OpenAlex更新：2026-09-05
  • 副分类：agent
  • 待LLM分类：否
  • 标题中文：S3Gym：LLM 能将自测试与自评判转化为自我提升吗？
  • TLDR中文：这些发现表明，仅识别成功动作并不足够；Agent 还需将反馈转化为可执行且可迁移的策略。本文给出统一框架以诊断该过程，并定位阻碍 Agent 将交互经验转化为可靠自我提升的瓶颈。
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-03-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]