Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
cs.LG
Submitted: 2026-10-15
Updated: 2026-10-15
Comments: 15 pages, 8 figures. Project page: https://zhaihaotian.github.io/MRTPO/
Code: https://github.com/zhaihaotian/MRTPO
Project page: https://zhaihaotian.github.io/MRTPO
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models
- AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
- Qwen2.5-Coder Technical Report
- DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
- GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
- RVPO: Risk-Sensitive Alignment via Variance Regularization
- Qwen2.5 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
- Qwen3 Technical Report
- CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
- Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL
- Instruction-Following Evaluation for Large Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks