GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
cs.LG, cs.AI
Submitted: 2026-10-06
Updated: 2026-10-13
Terminology
Sources
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark
- GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
- Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization
- ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
- When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents
- Self-Distilled Agentic Reinforcement Learning
- LLM Explainability with Counterfactual Chains and Causal Graphs
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey of On-Policy Distillation for Large Language Models
- BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
- APPO: Agentic Procedural Policy Optimization
- Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
- Qwen2.5 Technical Report
- Qwen3 Technical Report
- Self-Distilled RLVR
- OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
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