Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit

GPT-5.6 can design near-optimal algorithms for operations research problems like inventory control and queueing networks, matching or beating specialized methods with minimal human input.

Researchers propose CAST, a concept-guided fine-tuning framework using sparse autoencoders to make clinical language models more auditable and robust against deployment shifts.

Researchers present a scalable GNN system for friend recommendation that reduces embedding table size by 98% and improves temporal sampling efficiency, achieving 16% more friend additions in production tests.

CLAP is a cross-embodiment video world model framework that learns physical dynamics from diverse human and robot videos and achieves zero-shot simulation across different robot morphologies.

Research paper analyzes how language models organize moral knowledge using linear probes on Moral Foundations Theory categories across architectures.