Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Entropy-Aware On-Policy Distillation of Language Models
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- Multi-Turn On-Policy Distillation with Prefix Replay
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- Sequence Level Training with Recurrent Neural Networks
- Proximal Policy Optimization Algorithms
- A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
- TIP: Token Importance in On-Policy Distillation
- Qwen3 Technical Report
- ReAct: Synergizing Reasoning and Acting in Language Models
- SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
- SOD: Step-wise On-policy Distillation for Small Language Model Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks