Humanize: Judgement Engineering for Agentic Coding
Source
arxiv.org
Author
Sihao Liu, Ligeng Zhu, Zijian Zhang, Dongyun Zou, Zhengyang Zhang, Changye Li, Song Bian, Song Han, Tony Nowatzki
Date
Why it matters
Argues the writing AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → is a weak judge of completion, so completion should be decided by a reviewer from another vendor and enforced by deterministic gates. Directly reusable in coding agent loops.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleNot All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the WildObada Kraishan
articleZero2Repo: Can Coding Agents Build Repositories from Scratch?Pei Yang, Tianyu Shi, Yuhang Yao, Wanyi Chen, Tongyun Yang, Dun Pei, Haonan Wang, Pengbin Feng, Guanxu Yu, Jingchun Huang, Zeyu Zhang, Shuhan Sun, Hao Li, Xiang Li, Jie Xiao, Xinyu Wang, Hanxin Chen, Daqi Li, Qi Jia, Hongshan Lin, Zhizhou Gu, Zijun Tian, Weizhi Du, Lynn Ai, Eric Yang
articleA Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent AdoptionYegor Denisov-Blanch, Shyam Agarwal, Pavel Azaletskiy, Hao He, Rylan Schaeffer, Brando Miranda, Bogdan Vasilescu, Sanmi Koyejo