specific method · filed under evaluation
Pool
Pool is Poolside's agent harness used to run reproducible agentic coding evaluations on researchers' and developers' hardware.
Also called agentic coding evaluations run using pool.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
evaluations run using pool, Poolside's agent harness, so researchers and developers can reproduce the results on their own hardware
usedevaluation onlyin Laguna S 2.1Poolside
Filed alongside
Other methods under evaluation :: evaluation harness.
DeepSeek Harness Minimal modeHarborNeMo Evaluator SDKAtomic binary rubric evaluationAutomatic in-flight checkpoint evaluation schedulingBenchmark evaluation frameworkCross-scaffold evaluationInline training evaluatorsIsolated container per rolloutJSON-structured answer-format promptmini-swe-agent harnessNeMo Gym and NeMo Evaluator-based harnessNeMo Skills