LLM Agents
How Memory Architecture Shapes LLM Agent Performance
New research examines how different memory architectures affect LLM agent capabilities, offering insights into designing more effective AI systems.
AI Systems
AI Systems
SETA: A New Framework for Debugging Multi-Component AI Systems
Researchers introduce SETA, a statistical method for identifying which component in complex AI pipelines causes failures—critical for debugging multi-stage systems like video generation workflows.
LLM Infrastructure
PROTEUS: Lagrangian RL Optimizes Multi-LLM Routing for SLAs
New research introduces PROTEUS, a reinforcement learning framework using Lagrangian optimization to intelligently route requests across multiple LLMs while meeting strict service level agreements.
LLM Architecture
Uncertainty Architecture for Robust LLM Applications
A technical framework for designing LLM applications that explicitly handle uncertainty, covering architectural patterns, confidence scoring, and system design principles for building more reliable AI systems.
AI Agents
Study Reveals Key Role of Ideation Diversity in AI Agents
New research examines what makes effective AI research agents, finding that ideation diversity - the ability to generate varied approaches - is critical for autonomous research capabilities and agent performance.