UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/Zenghuang-Fu/Uniopsd
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
- Group-in-Group Policy Optimization for LLM Agent Training
- Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember
- Hindsight Credit Assignment
- Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
- Distilling the Knowledge in a Neural Network
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- The Role of Feedback Alignment in Self-Distillation
- CoEvoKG: Co-Evolving Knowledge Graphs with Self-Evolving Search Agents
- Conflict-Averse Gradient Descent for Multi-task Learning
- PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning
- Self-Distilled Policy Gradient
- Self-Distilled Agentic Reinforcement Learning
- On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
- Qwen2.5 Technical Report
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Reflexion: Language Agents with Verbal Reinforcement Learning
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