PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
cs.AI
Submitted: 2026-09-02
Updated: 2026-09-02
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Language Models are Few-Shot Learners
- Training Verifiers to Solve Math Word Problems
- Group-in-Group Policy Optimization for LLM Agent Training
- PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment
- Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning
- Constitutional AI: Harmlessness from AI Feedback
- GPT-4 Technical Report
- Training language models to follow instructions with human feedback
- SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution
- Gorilla: Large Language Model Connected with Massive APIs
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning
- Reflexion: Language Agents with Verbal Reinforcement Learning
- The Rise and Potential of Large Language Model Based Agents: A Survey
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Gemini: A Family of Highly Capable Multimodal Models
- TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
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
- 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
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection