TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- Process Reinforcement through Implicit Rewards
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- Distilling the Knowledge in a Neural Network
- BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent
- Reinforcement Learning via Self-Distillation
- VinePPO: Refining Credit Assignment in RL Training of LLMs
- Hindsight Compacts but Does Not Repair: Rethinking On-Policy Self-Distillation in Reasoning Models
- Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- On-policy Distillation with Verifiable Reward
- Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
- Self-Distilled Agentic Reinforcement Learning
- Improve Mathematical Reasoning in Language Models by Automated Process Supervision
- TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
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