Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL

cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/Ricardo-H/guide-then-let-go

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
• HDPO: Hybrid Distillation Policy Optimization via Privileged Self-Distillation
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
• 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
• RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
• AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
• SOD: Step-wise On-policy Distillation for Small Language Model Agents
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems