EvoPolicyGym Benchmark

What is EvoPolicyGym?

EvoPolicyGym evaluates autonomous policy evolution in interactive RL environments. A harness-model agent iteratively edits an executable policy under a fixed…

Released

2026-07-02

Evaluates

Agents & Tool Use, General AI, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.02440

EvoPolicyGym paper and code

• Paper https://arxiv.org/abs/2607.02440
• Code https://github.com/Linzwcs/EvoPolicyGym

Which sources cite EvoPolicyGym?

• EvoPolicyGym

Related Agents & Tool Use, General AI, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench
• ActiveSciBench