ExTra adds embedding-based novelty rewards and entropy-guided prefix regeneration to GRPO, improving pass@1 by ~5 and pass@16 by ~7 on math benchmarks with Qwen3-1.7B.
Mixed citations
Cde: Curiosity-driven exploration for efficient reinforcement learning in large language models.arXiv preprint arXiv:2509.09675
Mixed citation behavior. Most common role is background (50%).
9
Pith papers citing it
Background
50% of classified citations
citation-role summary
background 4
baseline 1
other 1
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9representative citing papers
SALT is a subspace-adaptive plug-in for GRPO that decomposes group-relative coefficients into shared and residual channels using mini-batch Gram geometry and amplifies residuals to mitigate signed cancellation in RLVR.
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
Kernel smoothing enables accurate low-variance value and gradient estimates for policy optimization in LLM reasoning under tight sampling constraints per prompt.
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
citing papers explorer
-
ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning
ExTra adds embedding-based novelty rewards and entropy-guided prefix regeneration to GRPO, improving pass@1 by ~5 and pass@16 by ~7 on math benchmarks with Qwen3-1.7B.
-
SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter
SALT is a subspace-adaptive plug-in for GRPO that decomposes group-relative coefficients into shared and residual channels using mini-batch Gram geometry and amplifies residuals to mitigate signed cancellation in RLVR.
-
Epistemic Uncertainty for Test-Time Discovery
UG-TTT adds epistemic uncertainty measured by adapter disagreement as an exploration bonus in RL for LLMs, raising maximum reward and diversity on scientific discovery benchmarks.
-
DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification
DeltaRubric decomposes multimodal preference evaluation into self-generated planning and verification steps within a single model, producing large accuracy improvements on VL-RewardBench via multi-role reinforcement learning.
-
Reinforcing Multimodal Reasoning Against Visual Degradation
ROMA improves MLLM robustness to seen and unseen visual corruptions by +2.3-2.4% over GRPO on seven reasoning benchmarks while matching clean accuracy.
-
Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning
Kernel smoothing enables accurate low-variance value and gradient estimates for policy optimization in LLM reasoning under tight sampling constraints per prompt.
-
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
A parameter-free sampling strategy called CUTS combined with Mixed-CUTS training prevents mode collapse in RL for saturated LLM reasoning tasks and raises AIME25 Pass@1 accuracy by up to 15.1% over standard GRPO.
-
Calibration-Aware Policy Optimization for Reasoning LLMs
CAPO improves LLM calibration by up to 15% while matching or exceeding GRPO accuracy through logistic AUC loss and noise masking, enabling better abstention and scaling performance.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.