arXiv:2609.10750v1 Announce Type: cross Abstract: LLM agents increasingly rely on external skills retrieved at runtime, making skill selection from large…
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
arXiv:2609.10762v1 Announce Type: cross Abstract: Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of…
Multilingual in Name Only? Cultural and Linguistic Weaknesses of LLMs in Urdu
arXiv:2609.10758v1 Announce Type: cross Abstract: Multilingual large language models (LLMs) are increasingly used for open-ended text generation, yet…
Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification
arXiv:2609.10752v1 Announce Type: cross Abstract: Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge…
AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow
arXiv:2609.10723v1 Announce Type: cross Abstract: Text-to-image diffusion transformers (DiTs) are powerful generators, yet direct prompting provides…
Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Improvement
arXiv:2609.10702v1 Announce Type: cross Abstract: Learning from limited text requires models to use context, generalize to new inputs, and retain useful…
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
arXiv:2609.10707v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines…
CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding
arXiv:2609.10744v1 Announce Type: cross Abstract: Autoregressive language models can be used to transform a payload text into a stegotext of identical…
The Truth Was Never Gone: Perfect Aliasing in Compliant-Context Truth Probes
arXiv:2609.10739v1 Announce Type: cross Abstract: A truth probe fitted where truthful reporting and a task’s prescribed action coincide cannot distinguish…
AI News Brief Hourly Summary 2026-09-12 14h : 11 posts
11 posts published in the last hour 11:33Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models 11:33Artificial Id: Drive and Persistent Alignment in Agentic AI 11:32A machine-checked proof of the Dong-Yang classification of optimal (n,4) binary codes for…
Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models
arXiv:2609.09957v1 Announce Type: cross Abstract: Modern large language models (LLMs) can translate natural-language descriptions into operations research…
Artificial Id: Drive and Persistent Alignment in Agentic AI
arXiv:2609.11911v1 Announce Type: new Abstract: Agentic AI is moving from bounded task execution toward systems that retain consequential state, continue…
A machine-checked proof of the Dong-Yang classification of optimal (n,4) binary codes for BSCs
arXiv:2609.10579v1 Announce Type: cross Abstract: We present a machine-checked Lean~4 formalization of Dong and Yang’s classification of optimal…
Can Edge-Deployable Vision-Language Models Identify Species?
arXiv:2609.11916v1 Announce Type: new Abstract: Camera traps often run in the field on edge hardware with limited or no connectivity, making small,…
Role differentiation as ignition of a collective information engine: Structuration in Agent Populations
arXiv:2609.05442v2 Announce Type: cross Abstract: Informational active matter shows how measurement-informed decisions produce collective order, so far in…
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
arXiv:2609.11859v1 Announce Type: new Abstract: How does a language model’s dependence on query-routing information and target knowledge change as it…
A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients
arXiv:2609.11768v1 Announce Type: new Abstract: Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge…
MindTopo: Can Foundation Models Reason in Topological Space?
arXiv:2609.11900v1 Announce Type: new Abstract: Spatial reasoning depends not only on metric properties such as distance, angle, and shape, but also on…