Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search
arXiv:2606.17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory)…
Infant Spontaneous Movement Noise Improves Exploration in Deep RL
arXiv:2606.16590v2 Announce Type: replace-cross Abstract: Exploration in deep reinforcement learning (RL) is commonly implemented as temporally uncorrelated white noise. However,…
AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor
arXiv:2606.17872v1 Announce Type: cross Abstract: Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their…
A Quantitative Analysis of Multimodal Biomarkers in Alzheimer’s Disease
arXiv:2606.17867v1 Announce Type: cross Abstract: Despite increasing adoption of multimodal approaches in Alzheimer’s Disease (AD) research — aimed at integrating…
Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations
arXiv:2606.15903v2 Announce Type: replace-cross Abstract: Where an LLM sits in an agent memory pipeline — between the recall plane that…
Data Augmentations for Data-Constrained Language Model Pretraining
arXiv:2606.16246v1 Announce Type: cross Abstract: As AI labs approach a data ceiling where compute capacity outpaces the rate of new…
Detect Before You Leap: Mirage Detection in Vision-Language Models
arXiv:2606.00435v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is…
Upper Bounds on the Generalization Error of Deep Learning Models via Local Robustness and Stability
arXiv:2606.16883v1 Announce Type: cross Abstract: Generalization is a critical property of data-driven models, particularly deep learning models deployed in safety-critical…
daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization
arXiv:2606.16497v1 Announce Type: cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is…
Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
arXiv:2512.07212v3 Announce Type: replace Abstract: Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions.…