LLMs learn self-regulated summarization of chain-of-thought steps via RL, allowing compressed Fold inference to reach the same accuracy as exhaustive Unfold mode with far lower token overhead.
45 * Only insert ‘<step>...</step>‘ tags with summaries between segments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
LLMs learn self-regulated summarization of chain-of-thought steps via RL, allowing compressed Fold inference to reach the same accuracy as exhaustive Unfold mode with far lower token overhead.