erictrainnlpinxihu / Grader-agentView on GitHub
Grader 的 agent 采用五阶段主循环:perceive→plan→act→observe→respond,由 harness 驱动。模型只决定意图与置信度,路由、工具集、风险等级由代码钉死。act 分只读 ReAct、RAG、人工提案、批量初批。四个写动作不在工具表,只能产提案。批改输出结构化 GradingDraft,逐条绑定 rubric 与段落 hash,保证可重放。
☆101Sep 28, 2026Updated 2 weeks ago

Alternatives and similar repositories for Grader-agent

Users that are interested in Grader-agent are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?