Learning from Teacher Continuations at Student States

arXiv:2609.36246 · cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.CL

Submitted: 2026-09-28

Updated: 2026-09-30

Project page: https://dylanzsz.github.io/olive

Terminology

• Distillation — 68× in this paper · explained in 2 episodes
• Benchmark — 14× in this paper · explained in 2 episodes
• Agentic Task — 13× in this paper · explained in 1 episode
• Agentic Tasks — 11× in this paper · explained in 1 episode
• On-Policy Distillation — 8× in this paper · explained in 3 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Trace — 6× in this paper · explained in 2 episodes
• Knowledge Distillation — 5× in this paper · explained in 11 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Covariate Shift — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Regret — 2× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes

Sources

• Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
• BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
• SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
• OpenThoughts: Data Recipes for Reasoning Models
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Distilling the Knowledge in a Neural Network
• Tmax: A simple recipe for terminal agents
• Trajectory-Refined Distillation
• Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
• Revisiting DAgger in the Era of LLM-Agents
• On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Spurious Rewards: Rethinking Training Signals in RLVR
• ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
• Kimi K3: Open Frontier Intelligence
• TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
• MiMo-V2-Flash Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering