# The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

Source: [arXiv](https://arxiv.org/abs/2607.24720v1)  
Feed7 permalink: https://feed7.dev/p/2607-24720v1-0gihy13  
Published: 2026-07-27T17:55:03.000Z  
Trust: Needs Review (needs_review)

## Why Included

Controlled experiments suggest long-horizon agent planning depends on explicit state transitions, some compositional trajectories, and compatible teacher patterns—not atomic skills alone.

## Source Summary

The study separates planning into **three stages**: acquisition in pre-training, shaping through GRPO or OPD, and integration through MOPD. Explicit state-transition modeling and even limited long-horizon data improved generalization, while suboptimal trajectories compounded errors.

## Practical Implication

For agent builders, the practical lesson is to train and evaluate complete trajectories, not just isolated tool skills. **OPD** had a broader useful region than GRPO in low-quality, long-horizon settings, and **MOPD** combined compatible planning patterns across environments.

## Agent-Ready Context

The study separates planning into **three stages**: acquisition in pre-training, shaping through GRPO or OPD, and integration through MOPD. Explicit state-transition modeling and even limited long-horizon data improved generalization, while suboptimal trajectories compounded errors.

For agent builders, the practical lesson is to train and evaluate complete trajectories, not just isolated tool skills. **OPD** had a broader useful region than GRPO in low-quality, long-horizon settings, and **MOPD** combined compatible planning patterns across environments.

Teacher knowledge is not automatically additive. Distilling unfamiliar procedures could damage the student's existing world model, while conflicting teacher patterns caused severe interference; the supplied material does not quantify these effects on production coding tasks.

## Context Map

- Layer: agent
- Domains: coding
- Topics: harness-engineering, multi-agent, agent-reliability

## Uncertainty

- Teacher knowledge is not automatically additive. Distilling unfamiliar procedures could damage the student's existing world model, while conflicting teacher patterns caused severe interference; the supplied material does not quantify these effects on production coding tasks.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.