Which Successes Make Good References? Action-Sequence Alignment for Multi-Turn On-Policy Distillation
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Group-in-Group Policy Optimization for LLM Agent Training
- Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
- Reinforcement Learning via Self-Distillation
- The Role of Feedback Alignment in Self-Distillation
- Kimi K3: Open Frontier Intelligence
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
- Multi-Turn On-Policy Distillation with Prefix Replay
- Multi-Turn Agent Self-Distillation with Compressed Hindsight
- When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
- Ray: A Distributed Framework for Emerging AI Applications
- Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models
- Privileged Information Distillation for Language Models
- Qwen2.5 Technical Report
- HybridFlow: A Flexible and Efficient RLHF Framework
- TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
- Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization
- Qwen3 Technical Report
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis