SOURCE-LINKED INTELLIGENCE

Persistent Teacher Anchoring for Tool-Using Agents

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Distillation is common in LLM post-training, where on-policy knowledge distillation (OPKD) uses student-generated trajectories to prepare the student for downstream RL. At each state, the student matches a next-token distribution supplied by the teacher. As the rollout enters states the teacher would not visit, the teacher-student distribution gap can accumulate. In tool use, this gap becomes consequential because student-written calls execute before supervision and their observations shape later prefixes. Proposer-verifier generation addresses this drift by letting the teacher decide which st

Read original source ↗ Open in workspace

recordType

paper

region

Global