ICT framework applies JS divergence to token logits to select critical tokens for selective RLVR updates, claiming 4.58% average pass@4 gains on Qwen2.5 models across seven reasoning benchmarks.
arXiv preprint arXiv:2509.25133 , year=
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
OrderGrad supplies unbiased likelihood-ratio and reparameterization gradient estimators for finite-sample L-statistics by applying a rank-based reward transformation usable in standard policy-gradient updates.
UCPO modifies GRPO with a uniformity penalty over correct solutions to prevent diversity collapse in RLVR, yielding up to 10% higher Pass@64 on AIME24 and 45% more equation-level diversity.
Replacing GRPO's fixed clipping range with a task-wise entropy-aware adaptive bound stabilizes multi-task agentic LLM training by synchronizing exploration-exploitation paces.
Proposes MaxPO using a Leave-Two-Out baseline for centered unbiased advantages in max@K policy gradients, with a unified derivation of finite-batch estimators.
SAGE reshapes the reverse-KL anchor via guide function q(x,y) for controllable empirical support expansion, yielding gains in both pass@1 and pass@k on math reasoning benchmarks.
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
Novice programmers completed more tasks with lower workload using GitHub Copilot versus a human partner, but reported significantly more positive and arousing emotions with the human teammate.
citing papers explorer
-
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
ICT framework applies JS divergence to token logits to select critical tokens for selective RLVR updates, claiming 4.58% average pass@4 gains on Qwen2.5 models across seven reasoning benchmarks.
-
OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation
OrderGrad supplies unbiased likelihood-ratio and reparameterization gradient estimators for finite-sample L-statistics by applying a rank-based reward transformation usable in standard policy-gradient updates.
-
Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity
UCPO modifies GRPO with a uniformity penalty over correct solutions to prevent diversity collapse in RLVR, yielding up to 10% higher Pass@64 on AIME24 and 45% more equation-level diversity.
-
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Replacing GRPO's fixed clipping range with a task-wise entropy-aware adaptive bound stabilizes multi-task agentic LLM training by synchronizing exploration-exploitation paces.
-
On Advantage Estimates for Max@K Policy Gradients
Proposes MaxPO using a Leave-Two-Out baseline for centered unbiased advantages in max@K policy gradients, with a unified derivation of finite-batch estimators.
-
SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
SAGE reshapes the reverse-KL anchor via guide function q(x,y) for controllable empirical support expansion, yielding gains in both pass@1 and pass@k on math reasoning benchmarks.
-
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.
-
OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
Novice programmers completed more tasks with lower workload using GitHub Copilot versus a human partner, but reported significantly more positive and arousing emotions with the human teammate.