Pith. sign in

REVIEW 7 cited by

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

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 2502.12215 v2 pith:UPFS2BOU submitted 2025-02-17 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords scalingmodelstest-timecapabilitiesparallelcotslimolonger
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The advent of test-time scaling in large language models (LLMs), exemplified by OpenAI's o1 series, has advanced reasoning capabilities by scaling computational resource allocation during inference. While successors like QwQ, Deepseek-R1 (R1) and LIMO replicate these advancements, whether these models truly possess test-time scaling capabilities remains underexplored. This study found that longer CoTs of these o1-like models do not consistently enhance accuracy; in fact, correct solutions are often shorter than incorrect ones for the same questions. Further investigation shows this phenomenon is closely related to models' self-revision capabilities - longer CoTs contain more self-revisions, which often lead to performance degradation. We then compare sequential and parallel scaling strategies on QwQ, R1 and LIMO, finding that parallel scaling achieves better coverage and scalability. Based on these insights, we propose Shortest Majority Vote, a method that combines parallel scaling strategies with CoT length characteristics, significantly improving models' test-time scalability compared to conventional majority voting approaches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Test-Time Scaling with Reflective Generative Model

    cs.LG 2025-07 conditional novelty 6.0 of 10

    MetaStone-S1 combines a shared policy and self-supervised process reward head to select high-quality reasoning traces, reaching o3-mini-level scores at 32B parameters.

  2. AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A stochastic scheduling framework that modulates slow-to-fast reasoning in large reasoning models at test time, improving accuracy while reducing token usage.

  3. Reasoning LLMs are Wandering Solution Explorers

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Six current reasoning LLMs, including commercial systems, exhibit structured-search failures on verifiable computation tasks and degrade as the solution space grows.

  4. OpenCodeReasoning-II: A Simple Test Time Scaling Approach via Self-Critique

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A 2.5M-example code reasoning dataset with critique traces enables Qwen2.5-based models to surpass prior open-weight distilled models on LiveCodeBench via test-time self-critique selection.

  5. Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A semantic entropy-guided stopping rule for multi-round parallel LLM reasoning improves accuracy while reducing inference steps on five benchmarks.

  6. Reasoning or Not? A Comprehensive Evaluation of Reasoning LLMs for Dialogue Summarization

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Explicit reasoning LLMs do not improve dialogue summarization quality and tend to be more verbose and less faithful than their non-reasoning counterparts.

  7. 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.

Pith tools