arXiv Machine Learning
Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
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.
arXiv Machine Learning
Sep 30
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
arXiv:2609.36864v1 Announce Type: new Abstract: Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling com...
arXiv Machine Learning
Oct 8
BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation
arXiv:2610.09804v1 Announce Type: new Abstract: Reinforcement learning is now central to eliciting reasoning in large language models, while in the popular algorithm Group Relative Policy Optimizatio...
arXiv Machine Learning
Jun 25
Learning with a Single Rollout via Monte Carlo Pass@k Critic
arXiv:2606. 25451v1 Announce Type: new Abstract: Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive.
arXiv AI
Aug 25
Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning
arXiv:2608.21501v1 Announce Type: new Abstract: Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport oper...
Hugging Face Trending Papers
Jun 17
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
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. Existing token-level credit assignment methods require resources beyond the model's own rollouts.