0

Longcot Env

Fresh

LongCoT medium + hard long-horizon reasoning (logic/cs/chemistry/chess/math) solved by an agent in a sandbox, scored by upstream longcot.verify.

Type
RL Env
Publisher
Prime Intellect
Capabilities
Long Context
Tags
V1Agentic
Runtime
multi-turn
License
unknown
Size
v0.1.1
Published
Sep 2026
Updated
Sep 2026
Canonical
app.primeintellect.ai/dashboard/environments/primeintellect/longcot-env

Cite

Notes

Only stored in your browser.

Attribution

Attribution policy →

longcot_env

Long-horizon reasoning tasks spanning five domains (logic, cs, chemistry, chess, math) at medium and hard difficulty. Each self-contained prompt embeds the full task; the agent writes its final answer to /workspace/answer.txt, which is scored via the upstream longcot.verify template dispatch (with a local numeric-equivalence fallback for math templates).

Taskset

  • Source: LongHorizonReasoning/longcot
  • Size: ~2,000 tasks (medium + hard across all five domains), loaded from the bundled JSON in the longcot package via load_questions

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.
  • 2026-06-24: Initial v1 taskset.