Pith. sign in

REVIEW 5 cited by

Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.20339 v1 pith:KID56CIH submitted 2025-02-27 cs.CL cs.AI

classification cs.CLcs.AI
keywords modelsperformancescalinginferencecomputationalcomputedistilledfixed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT) trajectories and aggregating their outputs through various selection mechanisms. This raises a fundamental question: can models with lower complexity leverage their superior generation throughput to outperform similarly sized Transformers for a fixed computational budget? To address this question and overcome the lack of strong subquadratic reasoners, we distill pure and hybrid Mamba models from pretrained Transformers. Trained on only 8 billion tokens, our distilled models show strong performance and scaling on mathematical reasoning datasets while being much faster at inference for large batches and long sequences. Despite the zero-shot performance hit due to distillation, both pure and hybrid Mamba models can scale their coverage and accuracy performance past their Transformer teacher models under fixed time budgets, opening a new direction for scaling inference compute.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning

    cs.CL 2026-08 conditional novelty 6.0 of 10

    Reasoning-enabled LLMs show more robust performance on Theory of Mind tests under prompt and task perturbations, supporting a robustness-based reading of recent gains.

  2. Raven: High-Recall Sequence Modeling with Sparse Memory Routing

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Raven is a linear-time sequence model whose sparse, input-dependent routing writes tokens into dedicated memory slots, preserving long-context recall and extrapolating 16x beyond training length.

  3. Kinetics: Rethinking Test-Time Scaling Laws

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A memory-aware test-time scaling law shows small models are overestimated and sparse attention is needed for efficient scaling.

  4. Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A comprehensive review that categorizes methods for shortening and adaptively triggering chain-of-thought reasoning in large language models.

  5. Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models

    cs.AI 2025-05 reject novelty 2.0 of 10

    A probabilistic saturation model for test-time scaling is proposed and fitted to reasoning benchmarks, but the plateau 'prediction' is computed from the same per-problem data used to measure it.

Pith tools