Is Discrete Difficulty Sufficient? Leveraging Continuous Difficulty for Efficient Self-Consistency in LLMs

• URL: http://arxiv.org/abs/2608.24590v1
• Date: Tue, 25 Aug 2026 14:17:30 GMT
• Title: Is Discrete Difficulty Sufficient? Leveraging Continuous Difficulty for Efficient Self-Consistency in LLMs
• Abstract summary: Self-Consistency (SC) is a decoding strategy that samples diverse reasoning paths and selects the most consistent answer.<n>The excessive token consumption incurred by generating multiple reasoning paths has been identified as a major limitation of SC.<n>We propose Flexible Self-Consistency (FSC), which estimates problem difficulty as a continuous signal and dynamically adjusts the number of generated reasoning paths.
• Score: 11.780939486930398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-Consistency (SC) is a decoding strategy that samples diverse reasoning paths and selects the most consistent answer, demonstrating strong performance on complex reasoning problems. However, the excessive token consumption incurred by generating multiple reasoning paths has been identified as a major limitation of SC. To improve computational efficiency, several studies have proposed strategies that adjust the number of reasoning paths or allocate resources differentially according to problem difficulty. Nevertheless, most existing methods categorize difficulty into a few fixed levels, failing to fully capture the continuously varying nature of reasoning complexity. In this work, we propose Flexible Self-Consistency (FSC), which estimates problem difficulty as a continuous signal and dynamically adjusts the number of generated reasoning paths accordingly. FSC predicts the output entropy of an input question using a pre-trained probe and leverages it as an indicator of model uncertainty to flexibly control the sampling budget. Experimental results show that, across various models and benchmarks, FSC maintains accuracy comparable to SC while achieving token savings of up to 76%.

Related papers

• CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models [18.894895416263296]
  Confidence-Adaptive Thinking (CAT) is a framework that incorporates the model's intrinsic self-certainty signals as confidence into the preference optimization process.<n>Our work enables LRMs to effectively compress confident responses while deliberating on uncertain ones, offering a potentially robust solution for balancing accuracy and latency in practical industrial scenarios.
  arXiv  Detail & Related papers  (2026-07-01T12:27:14Z)
• SuCo: Sufficiency-guided Continuous Adaptive Reasoning [59.17222918775686]
  Large Reasoning Models (LRMs) often generate excessively long Chain-of-Thoughts (CoT)<n>Existing efforts to mitigate this inefficiency typically rely on discrete reasoning modes or fixed budget tiers.<n>We introduce Minimal Sufficient CoT (MSC), defined as the shortest prefix of a CoT trajectory which is adequate for producing the correct answer.
  arXiv  Detail & Related papers  (2026-06-16T08:52:15Z)
• CAMD: Coverage-Aware Multimodal Decoding for Efficient Reasoning of Multimodal Large Language Models [48.33850939857255]
  We develop a theoretical framework that links sampling coverage, instance difficulty, and residual risk.<n>Our analysis reveals that multimodal reasoning exhibits a heavy-tailed difficulty distribution.<n>We propose Coverage-Aware Multimodal Decoding (CAMD), an adaptive inference mechanism that dynamically allocates according to estimated uncertainty.
  arXiv  Detail & Related papers  (2026-03-16T02:31:03Z)
• Think Twice Before You Write -- an Entropy-based Decoding Strategy to Enhance LLM Reasoning [32.332197731504046]
  Decoding strategies play a central role in shaping the reasoning ability of large language models.<n>Traditional methods such as greedy decoding and beam search often suffer from error propagation.<n>We propose an entropy-guided decoding framework that introduces token-level adaptivity into generation.
  arXiv  Detail & Related papers  (2026-03-10T23:08:26Z)
• Breaking the Pre-Sampling Barrier: Activation-Informed Difficulty-Aware Self-Consistency [10.079669716138763]
  Self-Consistency (SC) is an effective decoding strategy that improves the reasoning performance of Large Language Models (LLMs)<n>It suffers from substantial inference costs because it requires a large number of samples.<n>We propose Activation-Informed Difficulty-Aware Self-Consistency (ACTSC) to address these limitations.
  arXiv  Detail & Related papers  (2026-02-10T06:05:11Z)
• ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping [54.37497695483689]
  We propose ARES, a unified framework for adaptive reasoning that dynamically allocates exploration effort based on task difficulty.<n>Our approach is motivated by two key empirical findings: (i) while single-token entropy is noisy, high window-entropy (HWE) tokens can reliably capture reasoning-critical moments.<n>In the Adaptive Cold-Start stage, we curate multimodal and textual data paired with reasoning traces of length proportional to problem difficulty, equipping the model with initial difficulty awareness.<n>In the second stage, we develop Adaptive Entropy Policy Optimization (AEPO), which uses HWE tokens as exploration triggers
  arXiv  Detail & Related papers  (2025-10-09T17:03:28Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• PATS: Process-Level Adaptive Thinking Mode Switching [53.53401063490537]
  Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty.<n>This neglect of variation in task and reasoning process complexity leads to an imbalance between performance and efficiency.<n>Existing methods attempt to implement training-free fast-slow thinking system switching to handle problems of varying difficulty, but are limited by coarse-grained solution-level strategy adjustments.<n>We propose a novel reasoning paradigm: Process-Level Adaptive Thinking Mode Switching (PATS), which enables LLMs to dynamically adjust their reasoning strategy based on the difficulty of each step, optimizing the balance between
  arXiv  Detail & Related papers  (2025-05-25T17:58:50Z)
• Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective [27.94738910330893]
  Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models.<n>Existing methods attempt to improve efficiency by scheduling problems based on problem difficulties.<n>This paper introduces $textbfC$ompetence-$textbfD$ifficulty, which enables accurate and stable estimation of problem difficulties.
  arXiv  Detail & Related papers  (2025-05-23T09:15:26Z)
• MindFlayer SGD: Efficient Parallel SGD in the Presence of Heterogeneous and Random Worker Compute Times [49.1574468325115]
  We investigate the problem of minimizing the expectation of smooth non functions in a setting with multiple parallel workers that are able to compute optimal gradients.<n>A challenge in this context is the presence of arbitrarily heterogeneous and distributed compute times.<n>We introduce MindFlayer SGD, a novel parallel SGD method specifically designed to handle this gap.
  arXiv  Detail & Related papers  (2024-10-05T21:11:32Z)
• Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning [19.408941114068444]
  Self-consistency (SC) is a widely used decoding strategy for chain-of-thought reasoning.<n>Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples.<n>We propose Difficulty-Adaptive Self-Consistency (DSC), which leverages the difficulty information of batch queries to adaptively allocate inference resources.
  arXiv  Detail & Related papers  (2024-08-24T04:03:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.