On-Policy Visual Evidence Distillation
arXiv:2609.36838v1 Announce Type: cross Abstract: Visual agents solve problems by interleaving reasoning with image operations, and on-policy distillation (OPD) provides…
OpenAI-HuggingFace: A Reproduction & Lessons for Alignment Testing
arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI’s agents coordinated over channels outside their intended environment to breach Hugging…
KUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
arXiv:2609.37673v1 Announce Type: new Abstract: Experienced professionals know more than just facts and conclusions. They know which cues matter, why…
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement
arXiv:2609.35575v2 Announce Type: replace-cross Abstract: The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of…
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
arXiv:2609.36845v1 Announce Type: cross Abstract: Uncrewed aerial vehicle base stations (UAV-BSs) are expected to cover traffic demand that shifts across…
Tail-Weight Control and Localized Generalization in Nearly Low-Rank Adversarial Classification
arXiv:2609.23688v3 Announce Type: replace-cross Abstract: Empirical ramp fitting can assign weight to pure-noise features even when the population optimum ignores…
TokenCast: Forecasting Token Consumption During LLM Agent Execution
arXiv:2609.35760v2 Announce Type: replace-cross Abstract: When a large language model (LLM) agent executes the same task, token consumption can vary…
Beyond Forecasting: Recasting Volatility Control as a Routing Problem
arXiv:2608.10375v2 Announce Type: replace-cross Abstract: Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a…
The Linear Representation Hypothesis for Vision-Language-Action Models
arXiv:2609.30996v1 Announce Type: cross Abstract: The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on…
Accounting for Bias Enables Sustainable LLM Evaluation
arXiv:2609.31184v1 Announce Type: new Abstract: LLM-as-a-judge has become the de facto standard for scalable, subjective evaluation, yet current leaderboards compensate…