Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement

Media reports Hugging Face Papers Source language: Chinese

论文摘要(作者报告,未经本站复测):Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks.

Full text

Exposing benchmark success criteria to self-improving embodied coding agents can raise measured success under those criteria without improving instructed-task completion, and the advantage weakens under slight criteria changes and transfers poorly across tasks, while instruction-faithful criteria better reflect instructed-task performance.

Sources

← Back to Daily AI Report