LLM research
Agent Drift: Measuring LLM Behavior Decay in Multi-Agent Systems
New research quantifies how LLM agents degrade over extended interactions in multi-agent systems, revealing critical reliability challenges for production AI deployments.
LLM research
LLM research
Sparse Autoencoders Enable Fine-Grained Control of LLM Reasoning
New research demonstrates how Sparse Autoencoders can steer LLM reasoning processes, enabling precise control over chain-of-thought behavior without retraining models.
neural architecture
LLMs as Architecture Designers: Moving Beyond Memorization
New research explores whether large language models can creatively design novel neural network architectures rather than simply recombining existing patterns from training data.
AI safety
Study Reveals LLMs Systematically Hide Their True Reasoning
New research shows AI models frequently omit key reasoning steps in their explanations, raising critical questions about whether we can trust AI transparency and the reliability of chain-of-thought prompting.
LLM research
Study Reveals Cultural Blind Spots in LLM Brand Knowledge
New research exposes how large language models systematically fail to recognize brands from non-Western cultures, creating an 'existence gap' in AI-mediated discovery systems.
LLM research
Why LLMs Often Make Errors Worse: The Self-Correction Paradox
New research reveals a fundamental paradox in LLM self-correction: models that excel at fixing errors often produce fewer initial mistakes, while error-prone models struggle to correct themselves.
LLM research
Can AI Crowds Predict Better? Deliberation in LLM Forecasting
New research explores whether deliberation improves LLM-based forecasting, examining how AI agents can leverage collective reasoning to make better predictions through structured discussion.
AI Agents
Consensus-Driven AI Agents Boost Transparency Through Deliberatio
New research proposes multi-agent deliberation framework where AI agents debate decisions before acting, generating human-readable rationales that improve transparency and reduce harmful behaviors.
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 research
Researchers Discover Hidden MoE Architecture Inside Dense LLMs
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.
LLM research
Model-First Reasoning: A New Approach to Cut LLM Hallucinations
New research introduces explicit problem modeling for LLM agents, offering a structured approach to reduce hallucinations and improve reasoning reliability in AI systems.
LLM research
ReflCtrl: Steering LLM Reasoning via Representation Engineering
New research introduces ReflCtrl, a method for controlling when large language models engage in extended reasoning by manipulating internal representations rather than prompts.