STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.
Naturalthoughts: Selecting and distilling reasoning traces for general reasoning tasks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.
citing papers explorer
-
STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
STOP uses structured on-policy analysis to prune long reasoning traces to their earliest correct node, cutting token usage 19-42% with little accuracy loss on math benchmarks.
-
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
CoRD uses collaborative multi-teacher step-wise decoding with perplexity-guided beam search to generate higher-quality Long-CoT data that lets smaller models reach near-teacher performance with less supervision.
-
Characterizing Model-Native Skills
Recovering an orthogonal basis from model activations yields a model-native skill characterization that improves reasoning Pass@1 by up to 41% via targeted data selection and supports inference steering, outperforming human-characterized alternatives.