Pith. sign in

Title resolution pending

With the increase of self-improvement training iterations, both STaR, ReSTEM exhibit a trend where performance initially improves but then declines, which is similar to the findings of Ding et al · 2025 · arXiv 4343.9145

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

1 Pith paper citing it
read on arXiv 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.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Better, Faster: Harnessing Self-Improvement in Large Reasoning Models

cs.CL · 2026-05-24 · unverdicted · novelty 6.0

HSIR improves self-improvement for LRMs via verify-then-exit sampling and intrinsic diversity scoring, delivering up to 10.9% performance gains and 42.4% lower inference overhead across post-training methods including H-GRPO.

citing papers explorer

Showing 1 of 1 citing paper.

  • Better, Faster: Harnessing Self-Improvement in Large Reasoning Models cs.CL · 2026-05-24 · unverdicted · none · ref 4

    HSIR improves self-improvement for LRMs via verify-then-exit sampling and intrinsic diversity scoring, delivering up to 10.9% performance gains and 42.4% lower inference overhead across post-training methods including H-GRPO.