Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Agentic Tasks
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-13
Terminology
Sources
- Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation
- GLM-5: from Vibe Coding to Agentic Engineering
- The Llama 3 Herd of Models
- Editing Models with Task Arithmetic
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Temporal Sampling for Forgotten Reasoning in LLMs
- MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
- The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
- Qwen3 Technical Report
- Early Weight Averaging meets High Learning Rates for LLM Pre-training
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- AgentPatch: Coarse-to-Fine Weak-Task Repair for Merging Agentic Multimodal Large Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
- AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
- DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
- Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- SOD: Step-wise On-policy Distillation for Small Language Model Agents
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