Feng

A new framework for AI observability, proposed by Sisodia and based on research by Feng et al., introduces propositional probes that can extract a large language model's true internal beliefs even whe…

A PhD student released CMG, an open-source tool that audits LLM-based judges by requiring them to back each verdict with explicit claims tied to evidence, flagging untrustworthy decisions without usin…

Feng et al. published Group-in-Group Policy Optimization for LLM Agent Training at NeurIPS 2025, introducing a method that provides step-level credit to long-horizon LLM agents without a critic. An in…