HuggingFace Daily Papers· Haibo Jin, Peng Kuang, Xiaopeng Yuan, Lucheng Fu, Jerry Wang, Xucheng Yu, Yaoning Yu, Dehao Wu, Runguo Li, Colin Su, Jingxuan Sun, Xuyang Liu, Haojing Luo, Haohan Wang·· 4 天前精选AI 评分75
The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks
AI 导读
论文提出Agent原生原语(HEELO框架)，通过将资源与内置LLM结合，解决了AI模型在真实世界任务中'最后一公里'问题。实验显示，在Terminal-Bench 4.0上，GPT-5.6 Sol完成率从37.3%提升至55.5%，Claude Opus 5.5通过HEELO完成真实任务数从9提升至39，时间减少1.9倍，成本降低1.55倍。
推荐理由
从37.3%到55.5%，Agent原生原语让模型在真实世界任务完成率提升近20个百分点，但如何规模化验证仍是挑战。
来源：HuggingFace Daily Papers · arxiv.org