Teaching the Harness：面向 LLM 智能体的学生感知技能迁移方法 SAT
Teaching the Harness: Student-Aware Skill Transfer for LLM Agents
AI 导读
arXiv 论文提出 Student-Aware Teaching（SAT），让更强的 LLM 教师模型先建立学生模型、用诊断性探针检验假设，再为诊断出的失败写入可复用技能。
正文 · 原文
Abstract:Effective teaching requires reasoning about the learner as well as the task, a capacity that Theory of Mind describes as inferring another agent's latent state from its behavior. We ask whether a stronger LLM teaches a fixed student better when it applies this principle. The student is an LLM agent acting through a harness that fixes its tools, context, and action budget, so a procedure that helps one model can exhaust the budget of another. We introduce Student-Aware Teaching (SAT). The teacher builds a learner model that pairs an empirical profile with hypotheses about the student's limitations, tests these hypotheses with diagnostic probes, and writes reusable skills for the diagnosed failures. A skill enters the library only after it raises success on matched development tasks. With Claude-Sonnet-5 teaching DeepSeek-V4-Flash, SAT reaches 86.46% task success across four primary runs, leading both a profile-free teacher with the same framework (81.04%) and the untaught student (75.00%) in each run. Removing the analytical learner model lowers both prediction and success, and under misleading learner profiles none of the 48 candidate skills passes admission. When DeepSeek-V4-Flash and Gemini-3.8-Flash exchange libraries, each performs better with its own. Saved libraries keep average gains of up to 11.1 points after the teacher leaves. The benefit depends on a student that can follow instructions and a deployment route that delivers them.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13144 [cs.AI] |
| (or arXiv:2611.13144v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13144 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chang Liu [view email]
[v1]
Mon, 9 Nov 2026 19:23:42 UTC (133 KB)
来源：arXiv cs.AI · arxiv.org