arXiv AI
Semifactual Credit-Augmented Policy Optimization
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 29
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
arXiv:2607. 25659v1 Announce Type: new Abstract: Rubric-based reinforcement learning enriches language model training by evaluating model outputs against explicit criteria.
arXiv AI
Jun 2
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
arXiv:2605. 12969v3 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reasoning tasks.
arXiv Machine Learning
Jun 4
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
arXiv:2601. 07408v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks.
arXiv AI
Jun 2
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
arXiv AI
Jul 10
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
arXiv:2607. 07976v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs).
arXiv AI
Jun 18
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
arXiv:2606. 18810v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as GRPO assign uniform credit across all tokens, wasting gradient on routine tokens while under-crediting pivotal reasoning steps.