Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit Assignment
cs.AI
Submitted: 2026-11-04
Updated: 2026-11-05
Code: https://github.com/AnnaXChun/ORSD
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
- Distilling the Knowledge in a Neural Network
- Reinforcement Learning via Self-Distillation
- Self-Distilled Agentic Reinforcement Learning
- Agent Lightning: Train ANY AI Agents with Reinforcement Learning
- Proximal Policy Optimization Algorithms
- Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning
- Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
- Co-Evolution of Policy and Internal Reward for Language Agents
- EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning
- RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
- Step-wise Rubric Rewards for LLM Reasoning
- Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
- Qwen3 Technical Report
- ReAct: Synergizing Reasoning and Acting in Language Models
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents