TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
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) trajectory-level KL objectives concentrate most of
Record details
Published: 7 July 2026
Source: arXiv
Category: Research
Topics: Regulation · Children & education · Agents & autonomy
Retrieved: 14 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.
Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation
HuggingFace Daily Papers · 14 July 2026
Multi-Turn On-Policy Distillation with Prefix Replay
HuggingFace Daily Papers · 15 July 2026
Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning
arXiv · 28 June 2026
AutoSynthesis: An agentic system for automated meta-analysis
arXiv · 16 July 2026
Balancing public health and individual autonomy: a study of Chinas vaccination policy
Journal of Medical Ethics (BMJ) · 22 July 2026
Open Veins of Algorithmic Auditing: Why AI Assessment Lags Behind Its Deployment in the Global South
arXiv · 23 July 2026
How to cite this record
ethics.ai (7 July 2026), “TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training,” evidence record 176, https://ethics.ai/record/176 (originally published by arXiv).
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.