0

I3 Science

Fresh

Science problems solved by an agent in a sandbox, scored with math-verify and an LLM-judge fallback.

Type
RL Env
Publisher
Prime Intellect
Tags
V1Science
Runtime
multi-turn
License
unknown
Size
v0.1.2
Published
Nov 2025
Updated
Sep 2026
Canonical
app.primeintellect.ai/dashboard/environments/primeintellect/i3-science

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →

i3-science

Science tasks solved by an agent in a sandbox. Each task poses a science question with a boxed final answer; scored with math-verify against the gold answer, with an LLM-judge fallback when math-verify can't confirm it.

Taskset

Changelog

  • 2026-09-03: Restore default solver network access by reverting the network_allow=[] default-deny policy introduced in #780; training rollouts need outbound network.
  • 2026-08-31: Yield task records on demand so bounded evaluations construct only the requested prefix.
  • 2026-06-25: Initial v1 taskset.