Pith. sign in

Polychromic objectives for reinforcement learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling

cs.LG · 2026-07-01 · unverdicted · novelty 6.0

QuasiMoTTo uses quasi-Monte Carlo to produce correlated yet marginally correct samples from language models, matching i.i.d. pass@k with 25-47% fewer samples on reasoning benchmarks and 50% fewer RL training steps.

citing papers explorer

Showing 1 of 1 citing paper.

  • QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling cs.LG · 2026-07-01 · unverdicted · none · ref 13

    QuasiMoTTo uses quasi-Monte Carlo to produce correlated yet marginally correct samples from language models, matching i.i.d. pass@k with 25-47% fewer samples on reasoning benchmarks and 50% fewer RL training steps.