AI News

How to grow a cacao tree at home (www.cocoterra.com)

Gheist Uses Stolen GitHub Tokens to Steal Private Repository Secrets via Actions Logs (thehackernews.com)

Amazon Deforestation Fell To Lowest Level Since 1988 - And Silva Wins Reelection (news.slashdot.org)

Rosettes and Other Hidden Traces of Hamburg's Tram (alsterrunde.com)

The result of the C++26 DIS ballot (train-it.eu)

Tiny magnetic vortices could help computers work more like your brain (www.sciencedaily.com)

Malicious File in Downloads Folder Tries to Trick AI Coding Agent Into Installing Malware (thehackernews.com)

Veille quotidienne — 26/10/2026

Firmus data centres: Experts warn Tasmania of stranded energy risk | The Mercury (www.themercury.com.au)

The Watch: Data Center Boom Puts Pressure On Us Water Supplies (publichealthwatch.org)

AllModels (www.producthunt.com)

SS United States to be sunk as largest artificial reef (divemagazine.com)

Microsoft Announces Open Source Tool Evaluating Your Software's Optimization For AI Coding Agents (news.slashdot.org)

Closing the Sea: Lessons from Ancient Mediterranean Blockades (maritime-executive.com)

Commentary: Virginia must put the brakes on data center development - Roanoke Times (roanoke.com)

Show HN: Proc-CLI – An agent-friendly CLI tool for process and port management (proc-cli.com)

Cognitive Mercantilism: AI panic resembles fears of early capitalism (contraptions.venkateshrao.com)

DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage (arxiv.org)

LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents (arxiv.org)

FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification (arxiv.org)

Spectra: Multi-Scale Implicit Decomposition for Deepfake Detection (arxiv.org)

Do AI-for-Science Agents Preserve Model Safety? (arxiv.org)

ENCL: Enabling Efficient Neuromorphic Continual Learning with Local Learning Rule and Sub-Network Freezing Strategy (arxiv.org)

RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training (arxiv.org)

TTT in VLA Models: Exploring Training with Human Demonstrations (arxiv.org)

When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning (arxiv.org)

PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots (arxiv.org)

Reproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents (arxiv.org)

Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student? (arxiv.org)

CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition (arxiv.org)

Representation Learning via Composite Subspace Flow Matching (arxiv.org)

Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons (arxiv.org)

Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows (arxiv.org)

POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories (arxiv.org)

Compact-Bench: Measuring What Context Compaction Costs Long-Horizon Coding Agents (arxiv.org)

Softly Symbolifying Kolmogorov-Arnold Networks (arxiv.org)

Conformalized Polynomial Chaos Expansion for Uncertainty-aware Surrogate Modeling (arxiv.org)

PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean (arxiv.org)

From Dueling Bandits to Episodic MDPs: Learning with Adversarial Preference Feedback (arxiv.org)

Uniform ergodicity and spectral gap of importance-tempered MCMC with heavy-tailed targets (arxiv.org)

Knowing When to Stop: The Evidence-Action Gap in Coding Agents (arxiv.org)

Mixed Engression: Distributional Regression for Multivariate Mixed-Type Responses (arxiv.org)

Latent-Space Importance Weighting under Covariate Shift (arxiv.org)

Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services (arxiv.org)

Stochastic Inverse Problem: stability, regularization and Wasserstein gradient flow (arxiv.org)

Neural LoFi with Backward Coupling: A Spectral Theory of Cross-Layer Feature Learning (arxiv.org)

A Randomized Permutation Whole-Model Test Heuristic for Self-Validated Ensemble Models (SVEM) (arxiv.org)

Data Quality Audit and Bivariate Temperature-Humidity Analysis of a Long-Term LoRaWAN Network: Anomaly Detection, PCA, Clustering and Machine Learning (arxiv.org)

Understanding Communication Failures in Multi-Agent LLM Systems (arxiv.org)

Contextual Decision Making: Predictive or Generative (arxiv.org)