LLM Digest
Subscribe

AI Storyline

3 items · 3 sources · 3 days

View as JSON

Operational story trace

On-Policy Distillation

Latest change

Oct 22: an arXiv paper proposes advantage-based on-policy distillation, deciding per step when the student should follow the teacher.

Earlier contextThe story so far

Three arXiv papers from Oct 14–22 apply on-policy distillation (training a student on its own sampled trajectories, scored by a teacher) to different problems: machine translation, long-horizon coding agents, and the question of when the teacher should lead.

editor-curated · source-linked

Arc

Oct 14Oct 22 · now
TRANSLATION · Oct 14
Qwen-MT-Lumen applies on-policy training to WMT 2026 translation
1 source · show source ▾
CODING AGENTS · Oct 15
OPRD distills constraint reminders into long-horizon coding agents
1 source · show source ▾
NOW · Oct 22
Advantage-based method decides when to follow the teacher
1 source · show source ▾

What to watch — open questions

  • Does the advantage-based method beat plain on-policy distillation on agentic coding tasks, not only its own benchmarks?
  • Does any group release code that reproduces the OPRD long-horizon results?
How this thread was built
editor wrote the arc · 3 beats

Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.