arXiv AI
Jun 10
Learning Evidence Highlighting for Frozen LLMs
arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.
Reinforcement learning
Policy optimisation, reward modelling and RLHF — how models are trained by feedback rather than by labels.
arXiv AI
Jun 10
Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations
arXiv:2606. 10448v1 Announce Type: cross Abstract: The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC).
arXiv Machine Learning
Jun 10
Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies
arXiv:2605. 04254v3 Announce Type: replace Abstract: We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies.
arXiv AI
Jun 10
3SPO: State-Score-Supervised Policy Optimization for LLM Agents
arXiv:2606. 09961v1 Announce Type: cross Abstract: Training large language models (LLMs) as autonomous agents via reinforcement learning (RL) has enabled frontier models to achieve superhuman performance in long-horizon tasks.
arXiv AI
Jun 10
Dropout-GRPO: Variational Stochasticity for Continuous Latent Reasoning
arXiv:2606. 10184v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \mu_r$ collapses to zero.
arXiv AI
Jun 10
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
arXiv:2606. 10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains.
arXiv AI
Jun 10
Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning
arXiv:2606. 11087v1 Announce Type: cross Abstract: Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.
arXiv AI
Jun 10
SCOPE: Sequential Causal Optimization of Process Interventions
arXiv:2512. 17629v4 Announce Type: replace-cross Abstract: Prescriptive Process Monitoring (PresPM) recommends interventions during running business processes to optimize key performance indicators (KPIs).
arXiv AI
Jun 10
Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes
arXiv:2512. 14617v2 Announce Type: replace-cross Abstract: Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties.
arXiv Machine Learning
Jun 10
Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning
arXiv:2606. 10129v1 Announce Type: new Abstract: While deep Reinforcement Learning (deep-RL) has been increasingly applied to parameter control in evolutionary algorithms, rigorous theoretical analysis of parameter control remains largely restricted to single-parameter settings, owing to the difficulty of deriving effective, interpretable multi-parameter policies amenable to formal study.
arXiv Machine Learning
Jun 10
On-sky demonstration of reinforcement learning for adaptive optics control
arXiv:2606. 10771v1 Announce Type: cross Abstract: Reinforcement learning (RL)-based algorithms have recently emerged as a promising approach for adaptive optics (AO) control.
arXiv Machine Learning
Jun 10
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
arXiv:2509. 26000v3 Announce Type: replace Abstract: Asymmetric reinforcement learning leverages privileged information available during training to improve learning under partial observability.
arXiv AI
Jun 10
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces
arXiv:2606. 10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes.
arXiv Machine Learning
Jun 10
Replicable Bandits with UCB based Exploration
arXiv:2604. 20024v2 Announce Type: replace Abstract: We study replicable algorithms for stochastic multi-armed bandits (MAB) and linear bandits with UCB (Upper Confidence Bound) based exploration.
arXiv AI
Jun 10
RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning
arXiv:2606. 11092v1 Announce Type: cross Abstract: Elite humanoid soccer shooting requires whole-body stability, high-impulse whole-body interactions, and accuracy to targets.
arXiv Machine Learning
Jun 10
Alignment Defends LLMs from Property Inference Attacks
arXiv:2606. 10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties.
arXiv AI
Jun 10
Durable Evaluation Framework: Adversarial Arbitration for Sycophancy Reduction in Large Language Models
arXiv:2606. 07532v2 Announce Type: replace-cross Abstract: RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process.
arXiv AI
Jun 10
TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition
arXiv:2606. 09883v1 Announce Type: cross Abstract: Large language models (LLMs) have made remarkable progress in reasoning tasks, largely driven by post-training paradigms, especially reinforcement learning with verifiable rewards (RLVR).
arXiv AI
Jun 10
QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning
arXiv:2606. 09869v1 Announce Type: cross Abstract: Federated Learning (FL) combined with Split Learning (SL) is a privacy preserving paradigm that enables training deep neural networks (DNNs) on resource constrained devices while reducing overall training cost.
arXiv AI
Jun 10
Baseline-Free Policy Optimization for Neural Combinatorial Optimization
arXiv:2606. 10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems.