LLM Agents
New research introduces PABU, a framework that helps LLM agents track their progress and update beliefs more efficiently, reducing computational waste in multi-step reasoning tasks.
LLM Training
New research introduces neuron-level activation functions that leverage 2:4 structured sparsity to dramatically accelerate LLM pre-training while maintaining model quality.
LLM Agents
New research introduces Agent-Omit, a reinforcement learning framework that trains LLM agents to selectively omit unnecessary reasoning steps and observations, dramatically improving computational efficiency.
LLM Research
New research introduces Accordion-Thinking, a self-regulated approach that compresses reasoning steps dynamically to improve LLM efficiency while maintaining readable chain-of-thought outputs.
LLM Optimization
New research explores how quantization, batching strategies, and serving optimizations dramatically reduce LLM energy consumption while maintaining performance.
LLM
Quantization and fine-tuning techniques like QLoRA can reduce large language model sizes by 75% while preserving performance, enabling efficient AI deployment on consumer hardware.
LLM Research
New research reveals that standard dense language models contain secret Mixture-of-Experts structures, challenging our understanding of neural network architectures and opening paths to more efficient AI.
Agentic AI
Small language models are outperforming larger counterparts in agentic AI workflows due to speed, cost efficiency, and specialized task performance. Technical analysis reveals why compact models excel at autonomous decision-making.