Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

cs.CL · 2025-09-09 · conditional · novelty 6.0

Parallel-R1 uses SFT cold-start on easy math plus GRPO on hard math to instill parallel thinking in Qwen3-4B, reporting 8.4% average accuracy gains and a 42.9% AIME25 gain from a parallel-exploration scaffold.

citing papers explorer

Showing 1 of 1 citing paper.

  • Parallel-R1: Towards Parallel Thinking via Reinforcement Learning cs.CL · 2025-09-09 · conditional · none · ref 12

    Parallel-R1 uses SFT cold-start on easy math plus GRPO on hard math to instill parallel thinking in Qwen3-4B, reporting 8.4% average accuracy gains and a 42.9% AIME25 gain from a parallel-exploration scaffold.