Pith. sign in

REVIEW 16 cited by

A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning

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 2501.02497 v3 pith:CCFJREH6 submitted 2025-01-05 cs.AI cs.CLcs.LG

classification cs.AIcs.CLcs.LG
keywords computemodelstest-timesystem-2system-1modelreasoningcomplex
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The remarkable performance of the o1 model in complex reasoning demonstrates that test-time compute scaling can further unlock the model's potential, enabling powerful System-2 thinking. However, there is still a lack of comprehensive surveys for test-time compute scaling. We trace the concept of test-time compute back to System-1 models. In System-1 models, test-time compute addresses distribution shifts and improves robustness and generalization through parameter updating, input modification, representation editing, and output calibration. In System-2 models, it enhances the model's reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search. We organize this survey according to the trend of System-1 to System-2 thinking, highlighting the key role of test-time compute in the transition from System-1 models to weak System-2 models, and then to strong System-2 models. We also point out advanced topics and future directions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

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

  1. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

    cs.CL 2025-11 unverdicted novelty 7.0 of 10

    Evo-Memory is a new benchmark for self-evolving memory in LLM agents across task streams, with baseline ExpRAG and proposed ReMem method that integrates reasoning, actions, and memory updates for continual improvement.

  2. Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

    cs.AI 2026-05 conditional novelty 6.0 of 10

    Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.

  3. Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs

    cs.AI 2026-05 unverdicted novelty 6.0 of 10

    LRS trains a latent reward model on final-answer correctness to steer SAE states during inference, improving reasoning performance and implicitly encouraging better cognitive behaviors.

  4. When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

    cs.AI 2026-04 unverdicted novelty 6.0 of 10

    A disagreement-guided routing framework dynamically selects among resolution, voting, and rewriting strategies for test-time scaling, delivering 3-7% accuracy gains with lower sampling cost on mathematical benchmarks.

  5. When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.

  6. Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory

    cs.CL 2025-11 unverdicted novelty 6.0 of 10

    Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and ...

  7. SSSUMO: Real-Time Semi-Supervised Submovement Decomposition

    cs.HC 2025-07 conditional novelty 6.0 of 10

    SSSUMO is a semi-supervised neural network that decomposes movement velocity signals into submovements in real time, using synthetic data bootstrapped with self-generated labels.

  8. Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.

  9. Mapping Whisper Representations to Human ECoG Responses with Interpretable Time-Resolved Neural Encoding

    q-bio.NC 2026-06 unverdicted novelty 5.0 of 10

    The paper introduces a time-resolved neural encoder combining Whisper embeddings with recurrent temporal modeling and soft attention to predict ECoG responses, finding strongest alignment in intermediate layers and an...

  10. When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling

    cs.AI 2026-04 conditional novelty 5.0 of 10

    A disagreement-based router that decides per math problem whether to accept, majority-vote, or rewrite improves accuracy by 3–7% with fewer samples than fixed test-time scaling methods.

  11. Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness

    cs.AI 2025-09 unverdicted novelty 5.0 of 10

    Thinking LLMs achieve ~10 percentage points higher accuracy than non-thinking ones on RewardBench with under 2x compute overhead, outperforming augmentation strategies that cost over 8x more while also showing better ...

  12. R4ec: A Reasoning, Reflection, and Refinement Framework for Recommendation Systems

    cs.IR 2025-07 conditional novelty 5.0 of 10

    R4ec trains a small reflection model to critique and refine LLM-generated user and item knowledge, which then improves downstream recommendation accuracy.

  13. Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models

    cs.CL 2025-07 reject novelty 4.0 of 10

    A step-level verifier-guided hybrid of Best-of-N sampling, Monte Carlo tree search, and conditional self-refinement improves reasoning in small instruction-tuned LLMs, claiming up to 28.6-point gains.

  14. MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation

    cs.CL 2026-06 unverdicted novelty 3.0 of 10

    MODE-RAG introduces a VFE-driven multi-agent pipeline with MCTS and logit perturbations to lower hallucination and sycophancy rates in multimodal RAG, tested on the new ModeVent subset of MultiVent.

  15. OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems

    cs.AI 2026-04 reject novelty 3.0 of 10

    A review-plus-demo claiming agentic capabilities emerge from system integration, backed by a 15-task benchmark whose C1→C3 performance gap is largely built into the test design.

  16. From System 1 to System 2: A Survey of Reasoning Large Language Models

    cs.AI 2025-02 accept novelty 3.0 of 10

    The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.

Pith tools