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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Speech analysis of think-aloud protocols shows that transferable insights in insight problems are accompanied by spontaneous verbal labeling of problem types and faster performance gains.
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.
-
Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving
Speech analysis of think-aloud protocols shows that transferable insights in insight problems are accompanied by spontaneous verbal labeling of problem types and faster performance gains.