The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated. To address this challenge, we introduce a unified and controlled multi-turn environment that enables precise control. It allows systematically study long-horizon planning across three stages. (1) Planning abilit
Record details
Published: 27 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Regulation · Agents & autonomy · Environment
Retrieved: 28 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
HuggingFace Daily Papers · 26 July 2026
Constitutional governance for societies of AI agents in the built environment: a research agenda
arXiv cs.CY · 28 July 2026
Eco3S: Complex Socio-Economic System Simulation via Agent-Based Models
arXiv · 29 July 2026
Harness-G: A Graph-Structured Harness for Search Agents
HuggingFace Daily Papers · 29 July 2026
From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents
arXiv · 30 July 2026
On-Policy and Off-Policy Learning for Large Action Spaces
arXiv cs.AI · 30 July 2026
How to cite this record
ethics.ai (27 July 2026), “The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation,” evidence record 14029, https://ethics.ai/record/14029 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.