**摘要**
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification. We frame thi
👤 作者: Xuying Ning, Katherine Tieu, Dongqi Fu, Tianxin Wei, 李子豪, Yuanchen Bei, Jiaru Zou, Mengting Ai, Zhining Liu, Ting-Wei Li, Lingjie Chen, Yanjun Zhao, Ke Yang, Bingxuan Li, Cheng Qian, Gaotang Li, Xiao Lin, Zhichen Zeng, Ruizhong Qiu, Sirui Chen, Yifan Sun, Xiyuan Yang, Ruida Wang, Rui Pan, Chenyuan Yang, Dylan Zhang, Liri Fang, Zikun Cui, Yang Cao, Pan Chen, Dorothy Sun, Ren Chen, Mahesh Srinivasan, Nipun Mathur, Yinglong Xia, Hong Li, Hong Yan, Pan Lu, Lingming Zhang, Tong Zhang, HANGHANG TONG, Jingrui He

---
🔗 **[作为座席线束的代码](https://arxiv.org/abs/2605.18747v1)**

> Code as Agent Harness
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-20 05:37