EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%google/adk-go →
- PossiblePossibly related (embedding) · 56%AgentCore-8B →
- PossiblePossibly related (embedding) · 53%dyoshikawa/rulesync →
- PossiblePossibly related (embedding) · 53%alibaba/spring-ai-alibaba →
- PossiblePossibly related (embedding) · 53%DashAISoftware/dashAI →
- LinkedLinked via arxiv author · 85%Zhilin Wang →
“EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments”
- LinkedLinked via arxiv author · 85%Han Song →
“EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments”
- LinkedLinked via arxiv author · 85%Runzhe Zhan →
“EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments”