---
title: "TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training — Stuff That Spins"
description: "arXiv:2607.05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajec…"
	canonical: "https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training"
html: "https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training"
json: "https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training.json"
markdown: "https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-07-08T04:00:00+00:00"
modified: "2026-07-08T06:02:34.930509+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/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training#article","headline":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training","description":"arXiv:2607.05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajec…","datePublished":"2026-07-08T04:00:00+00:00","dateModified":"2026-07-08T06:02:34.930509+00:00","url":"https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training","mainEntityOfPage":{"@type":"WebPage","@id":"https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Artificial Intelligence","url":"https://export.arxiv.org/rss/cs.AI"},"publisher":{"@id":"https://stuffthatspins.com/#organization"},"citation":"https://arxiv.org/abs/2607.05804","about":[],"mentions":[{"@type":"Organization","name":"arXiv Artificial Intelligence"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Stuff That Spins","item":"https://stuffthatspins.com/"},{"@type":"ListItem","position":2,"name":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training","item":"https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training"}]}]}
---

# TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

**Source:** Unknown  
**Published:** July 8, 2026  
**Original:** https://arxiv.org/abs/2607.05804  

## On this page

- [Overview](#overview)

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

## Overview

arXiv:2607.05804v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student policy by matching a stronger teacher on the student's own trajectories, offering a promising framework for language agent training. However, its application to long-horizon agentic tasks remains insufficiently explored. We identify two key inefficiencies in vanilla agent OPD: (1) full-horizon rollouts often waste wall-clock resources on tail turns that provide weak and noisy KL supervision, and (2) tra

---
*HTML version: https://stuffthatspins.com/spin/turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-horizon-agent-training*