CortexOps and Langfuse are both open-source AI observability platforms, but they differ in focus: Langfuse traces LLM calls for prompt engineering and cost monitoring, while CortexOps traces full agen…
Researchers trained a small transformer encoder to detect reward hacking in reinforcement learning trajectories by mapping them onto a unit sphere where embedding distance approximates reward-metadata…
Researchers introduced ADHD, a method that fans out parallel divergent branches under different cognitive frames to prevent premature convergence in large language model agents. Across six open-ended …
Researchers introduced SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a code-augmented agentic optimizer that autonomously rewrites prompts using a Python sandbox for structural error analys…