self-consistency

This paper introduces MARS, a stopping rule for parallel LLM test-time scaling that probes partial traces to stop early without sacrificing accuracy, saving 25–47% of tokens across reasoning models on competition math benchmarks.

This paper proposes Behavior Forecasters, a learned approach that predicts an LRM's future behavior (e.g., answer consistency and input sensitivity) from its reasoning trajectory, outperforming GPT-5.4 and Claude Opus 4.6 at lower cost.

KACE introduces a knowledge-adaptive context engineering method that separates storage from usage via an epistemic tree and tiered self-consistency, achieving 62.2% on AIME 2025—a 10.4-point gain over fixed self-consistency.

This paper reveals that aggregating complete reasoning traces from multiple LLM agents, rather than just their final answers, can correct errors even when agents unanimously agree, introducing the 'aggregation paradox' and the Self-Consistent Mixture of Agents method.

This paper proposes a self-supervised framework using multilingual self-consistency and a self-critique mechanism to transfer cultural knowledge across languages, achieving a 5.03% average improvement on English queries in the BLEnD benchmark by surfacing latent cultural knowledge from local-language representations.

This paper introduces 'prefix consistency,' a method that weights candidate responses in Chain-of-Thought reasoning based on answer reproduction rates during trace regeneration. It achieves high accuracy with significantly fewer tokens than standard majority voting across various reasoning models and benchmarks.