Machine Heart

Jul 12, 2026 · Artificial Intelligence

Confidence‑Gated Reflection Boosts Reward Model Accuracy and Efficiency (CAMEL)

The CAMEL framework introduces a confidence‑gated reflection mechanism that uses the log‑probability margin between verdict tokens to decide whether a single‑token fast judgment suffices or a full generative reflection is needed, achieving 82.9% average accuracy—a 3.2% gain over prior best—while a 14B model outperforms several 70B‑scale reward models and offers a tunable accuracy‑cost trade‑off.