RL agent for online LHC trigger threshold tuning improves in-tolerance intervals by 28-56% on Monte Carlo and real CMS data without fine-tuning.
arXiv preprint arXiv:2603.01162 , year=
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 13roles
background 4representative citing papers
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
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.
Shows that under differentiable rollouts with additive noise, actor updates in critic-free RL for LLMs are value-gradient-like in expectation, motivating a decomposition into value signal and reward headroom for when RL is most effective.
A two-stage probe (hidden-state estimate plus attention-based correction) yields per-step GRPO rewards that survive prefix contamination and beat external-judge and tree-search rewards in the reported benchmarks.
A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.
DGPO is a critic-free RL framework that uses bounded Hellinger distance and entropy-gated advantage redistribution to enable fine-grained token-level credit assignment in long CoT generations for LLM alignment, reporting SOTA results on AIME benchmarks.
Kernel smoothing enables accurate low-variance value and gradient estimates for policy optimization in LLM reasoning under tight sampling constraints per prompt.
RTT bridges response-level rubrics to token-level rewards via a relevance discriminator and intra-sample group normalization, yielding higher instruction and rubric accuracy than baselines.
PointVG-R is a new MLLM that reaches SOTA on pointing localization by 15.86 mIoU points via a geometric reasoning pipeline, EgoPoint-CoT dataset, SFT, RL, and variance-based reward weighting.
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.
Perturbing the prefix before next-token prediction, during both training and inference, improves out-of-distribution language-model generation and yields a conditional extrapolation guarantee.
A statistical survey of RLHF for LLM alignment that connects preference learning and policy optimization to models like Bradley-Terry-Luce while reviewing methods, extensions, and open challenges.
citing papers explorer
-
Learning to Trigger: Reinforcement Learning at the Large Hadron Collider
RL agent for online LHC trigger threshold tuning improves in-tolerance intervals by 28-56% on Monte Carlo and real CMS data without fine-tuning.
-
CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning
CurveRL derives a quantile-coordinate reweighting rule from a utility functional on pass rates and shows it outperforms GRPO on reasoning benchmarks.
-
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.
-
Value-Gradient Hypothesis of RL for LLMs
Shows that under differentiable rollouts with additive noise, actor updates in critic-free RL for LLMs are value-gradient-like in expectation, motivating a decomposition into value signal and reward headroom for when RL is most effective.
-
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
A two-stage probe (hidden-state estimate plus attention-based correction) yields per-step GRPO rewards that survive prefix contamination and beat external-judge and tree-search rewards in the reported benchmarks.
-
Learning Perturbations to Extrapolate Your LLM
A learnable continuous perturbation framework for LLM token prefixes via latent vector transformations, optimized through unbiased estimating equations, yields gains in out-of-domain performance.
-
DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment
DGPO is a critic-free RL framework that uses bounded Hellinger distance and entropy-gated advantage redistribution to enable fine-grained token-level credit assignment in long CoT generations for LLM alignment, reporting SOTA results on AIME benchmarks.
-
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.
-
Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
RTT bridges response-level rubrics to token-level rewards via a relevance discriminator and intra-sample group normalization, yielding higher instruction and rubric accuracy than baselines.
-
PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought
PointVG-R is a new MLLM that reaches SOTA on pointing localization by 15.86 mIoU points via a geometric reasoning pipeline, EgoPoint-CoT dataset, SFT, RL, and variance-based reward weighting.
-
PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
PACEvolve++ uses a phase-adaptive reinforcement learning advisor to decouple hypothesis selection from execution in LLM-driven evolutionary search, delivering faster convergence than prior frameworks on load balancing, recommendation, and protein tasks.
-
Perturbation is All You Need for Extrapolating Language Models
Perturbing the prefix before next-token prediction, during both training and inference, improves out-of-distribution language-model generation and yields a conditional extrapolation guarantee.
-
Reinforcement Learning from Human Feedback: A Statistical Perspective
A statistical survey of RLHF for LLM alignment that connects preference learning and policy optimization to models like Bradley-Terry-Luce while reviewing methods, extensions, and open challenges.