Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning
Haoyu Zheng, Yun Zhu, Qing Wang, Wenqiao Zhang
cs.LG, cs.CL
Submitted: 2026-08-07
Updated: 2026-08-10
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Reinforcement Learning via Self-Distillation
- GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
- What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
- Self-Distilled Agentic Reinforcement Learning
- HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning
- Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents
- Qwen2.5 Technical Report
- VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- InstructSAM: Segment Any Instance with Any Instructions
- VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks
- PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
- TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous 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