EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? Paper β’ 2609.04280 β’ Published Sep 3 β’ 30
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind Paper β’ 2604.11666 β’ Published Apr 13 β’ 4
π Interpretability & Analysis of LMs Collection Outstanding research in LM interpretability and evaluation, summarized β’ 136 items β’ Updated May 26 β’ 120