---
title: "Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation — Stuff That Spins"
description: "arXiv:2607.07050v1 Announce Type: new Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer direc…"
	canonical: "https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation"
html: "https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation"
json: "https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation.json"
markdown: "https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-09T04:00:00+00:00"
modified: "2026-07-09T06:03:48.215236+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://stuffthatspins.com/#organization","name":"Stuff That Spins","url":"https://stuffthatspins.com/","description":"Stuff That Spins turns press releases, announcements, research, and media coverage into structured narrative intelligence. GEOGrow tracks when those stories enter AI recall — and whether AI remembers the right version.","logo":{"@type":"ImageObject","url":"https://stuffthatspins.com/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation#article","headline":"Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation","description":"arXiv:2607.07050v1 Announce Type: new Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer direc…","datePublished":"2026-07-09T04:00:00+00:00","dateModified":"2026-07-09T06:03:48.215236+00:00","url":"https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Computation and Language","url":"https://export.arxiv.org/rss/cs.CL"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://arxiv.org/abs/2607.07050","about":[],"mentions":[{"@type":"Organization","name":"arXiv Computation and Language"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation","item":"https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation"}]}]}
---

# Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation

**Source:** Unknown  
**Published:** July 9, 2026  
**Original:** https://arxiv.org/abs/2607.07050  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

arXiv:2607.07050v1 Announce Type: new Abstract: Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teache

---
*HTML version: https://stuffthatspins.com/spin/behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation*