Editorial Team

LLM Agents

GenEnv: Co-Evolving LLM Agents with Adaptive Environment Simulato

New research introduces GenEnv, a framework where LLM agents and environment simulators co-evolve through difficulty-aligned training, enabling more robust agent capabilities.

AI Agents

Inside AI Coding Agents: Architecture, Tools, and Agentic Loops

A technical deep dive into how AI coding agents work, from tool-calling mechanisms and agentic loops to planning systems and memory architectures that enable autonomous code generation.

speech recognition

Three-Stage LLM Framework Tackles ASR Errors and Hallucinations

New research introduces a verification-based approach to correct speech recognition errors while minimizing LLM hallucinations through structured multi-stage processing.

LLM Interpretability

Brain-Grounded Axes: Reading and Steering LLM Internal States

New research maps LLM internal representations to brain-derived axes, enabling interpretable reading and targeted steering of model behavior without fine-tuning.

AI Security

Adversarial Attacks on LLM Resume Screeners Reveal AI Security Ga

New research exposes how adversarial techniques can manipulate LLM-based resume screening systems, revealing fundamental security vulnerabilities in specialized AI applications.

LLM Agents

ABBEL: Language-Based Belief Bottlenecks Improve LLM Agents

New research introduces ABBEL, an architecture that constrains LLM agents to act through explicit belief states expressed in natural language, improving interpretability and decision-making in complex environments.

LLM research

Behavioral RL Method Tackles LLM Hallucinations Head-On

New research introduces Behaviorally Calibrated Reinforcement Learning to reduce AI hallucinations by aligning model confidence with actual accuracy, improving reliability in language models.

LLM-as-a-Judge

New Analytical Framework Explains LLM-as-a-Judge Scaling

Researchers present a mathematically tractable model for understanding how LLM-as-a-Judge systems scale during inference, offering insights into AI evaluation mechanisms.

AI Security

ArcGen: Cross-Architecture Backdoor Detection for Neural Networks

New research introduces ArcGen, a framework that generalizes neural backdoor detection across diverse model architectures without retraining, addressing critical AI security vulnerabilities.

LLM Training

How ChatGPT, Claude, and Gemini Are Trained: The 3-Stage Pipeline

Modern LLMs undergo three critical training stages: pretraining on massive text corpora, supervised fine-tuning for instruction following, and RLHF for alignment. Here's how the pipeline works.

deepfake detection

FaceOff Technologies Launches AI Deepfake Detection Engine

FaceOff Technologies unveils new AI-powered detection platform targeting deepfakes and synthetic fraud, aiming to strengthen digital trust infrastructure for enterprises.

ByteDance

ByteDance Plans $23B AI Infrastructure Investment for 2026

TikTok parent ByteDance commits $23 billion to AI infrastructure in 2026, signaling massive expansion of generative AI capabilities that could reshape video synthesis and content creation.