Pith. sign in

Title resolution pending

The MATH-500 ablation breakdown is omitted because the saturated regime provides little discriminative signal among the control conditions · 2024

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

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

TREK: Distill to Explore, Reinforce to Refine

cs.LG · 2026-07-06 · conditional · novelty 5.0

TREK uses verified teacher proposals to expand a student model's exploration support before standard GRPO refinement, improving performance on hard math and agentic tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • TREK: Distill to Explore, Reinforce to Refine cs.LG · 2026-07-06 · conditional · none · ref 29

    TREK uses verified teacher proposals to expand a student model's exploration support before standard GRPO refinement, improving performance on hard math and agentic tasks.