Process Advantage Signal Shaping: Advantage Construction for Process-Supervised Reinforcement Learning in LLM Reasoners
cs.AI
Submitted: 2026-06-28
Updated: 2026-10-10
Terminology
Sources
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
- Tackling Length Inflation Without Trade-offs: Group Relative Reward Rescaling for Reinforcement Learning
- FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
- Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
- What Makes a Reward Model a Good Teacher? An Optimization Perspective
- DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
- Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
- Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
- Qwen2.5 Technical Report
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