FIELD NOTES TOPIC
gpt-5.5
2 notes, newest first.
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
The paper introduces EvoPolicyGym, a new benchmark for evaluating how autonomous agents improve their executable policies through feedback in interactive environments. The authors use this benchmark to evaluate GPT-5.5…
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
The research introduces EvoPolicyGym, a controlled evaluation setting for autonomous agents to improve executable policies through feedback. The setting is designed to separate this process from a final score or…
