mlsanityData to 14 Oct 2026

Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling

arXiv 2605.15100 ↗First posted 14 May 2026cs.AIcited by 1

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling faces challenges in trade-off between sampling budget and reasoning quality. Current strategies remain inefficient as they typically treat sampling width and depth as orthogonal objectives, where width consensus methods risk reinforcing hallucinations, while depth pruning mechanisms prematurely truncate complex yet valid reasoning chains. Therefore, we propose Dual-Dimensional Consistency (DDC), a unified framework that bridges path quality with adaptive termination. By coupling Confidence-Weighted Bayesian protocol with a Trend-Aware Stratified Pruning, our method ensures that computational resources are concentrated on high quality reasoning paths, filtering hallucinations while accelerating consensus. Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 34 of its 51 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

34 of 51 references.

Closest ancestors · 15

Same direction, newest first

  1. 2026Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning6 Jan
  2. 2025Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning9 Oct
  3. 2025Deep Think with Confidence21 Aug
  4. 2025MUR: Momentum Uncertainty guided Reasoning for Large Language Models20 Jul
  5. 2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning16 May
  6. 2025φ-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation17 Mar
  7. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certainty25 Feb
  8. 2024Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning24 Aug
  9. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  10. 2024Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models1 Aug
  11. 2024Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning19 Jan
  12. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
3 more
  1. 2023Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs19 May
  2. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May
  3. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  8. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  9. 2020Learning to summarize from human feedbackcited by 2,588
  10. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 991
  11. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  12. 2025LIMO: Less is More for Reasoningcited by 498
7 more
  1. 2025TTRL: Test-Time Reinforcement Learningcited by 275
  2. 2024Detecting Hallucinations in Large Language Model Generation: A Token Probability Approachcited by 42
  3. 2024Non-myopic Generation of Language Models for Reasoning and Planningcited by 26
  4. 2024CriticEval: Evaluating Large Language Model as Criticcited by 13
  5. 2025Test-Time Model Adaptation for Quantized Neural Networkscited by 10
  6. 2024On the Performance Analysis of Momentum Method: A Frequency Domain Perspectivecited by 8
  7. 2025Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAGcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Rollouts to Recipes: Self-Contained Post-Training for LLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Enhancing reasoning accuracy in large language models during inference time
  2. 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
  3. 2025A Survey of Scaling in Large Language Model Reasoning
  4. 2024Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
  5. 2025The Art of Scaling Test-Time Compute for Large Language Models
  6. 2025Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
  7. 2026Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
  8. 2026NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning