arXiv (All)
open access
Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
On-policy distillation (OPD) trains agents on their own trajectories using supervision from a stronger teacher. We uncover a counterintuitive phenomenon in multi-turn agentic tasks: a smaller, initially weaker student can substantially outperform its teacher during training, only to regress as disti
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy Distillation#1144087
- Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation#1118121
- More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning#1354474
- Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation#1036937
- Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives#1143267
Record · ID 1389980
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive