LLM
Self-Generated Examples Boost LLM Reasoning Performance
New research reveals that LLMs reason better using their own examples rather than human-provided ones, suggesting the process of generation matters more than example quality.
reasoning
LLM Research
Accordion-Thinking: A New Method for Efficient LLM Reasoning
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.
AI Agents
Semantic Information Gain Rewards for Smarter AI Retrieval
New research introduces synthetic semantic information gain rewards to optimize when AI agents should retrieve external knowledge, improving reasoning efficiency without sacrificing accuracy.
LLM Research
Zero-Error LLM Reasoning Across Million-Step Tasks
New research demonstrates LLMs can complete million-step reasoning tasks with zero errors through novel verification and correction methods, advancing AI agent capabilities for complex multi-step workflows.