# The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute

arXiv: https://arxiv.org/abs/2511.02309 · HTML: https://mlsanity.com/paper/2511.02309/

## Key facts

- Cited by 11 papers 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 23 of its 32 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 23 of 23)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Teaching Large Language Models to Self-Debug](https://mlsanity.com/paper/2304.05128/) (2023)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [Inference-Time Scaling for Generalist Reward Modeling](https://mlsanity.com/paper/2504.02495/) (2025)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?](https://mlsanity.com/paper/2502.12215/) (2025)
- [Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search](https://mlsanity.com/paper/2503.04412/) (2025)
- [Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation](https://mlsanity.com/paper/2506.09991/) (2025)
- [Entropy-Gated Branching for Efficient Test-Time Reasoning](https://mlsanity.com/paper/2503.21961/) (2025)
- [Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey](https://mlsanity.com/paper/2507.09662/) (2025)
- [Scaling Inference-Efficient Language Models](https://mlsanity.com/paper/2501.18107/) (2025)
- [The Serial Scaling Hypothesis](https://mlsanity.com/paper/2507.12549/) (2025)
- [Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models](https://mlsanity.com/paper/2505.21765/) (2025)
- [SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models](https://mlsanity.com/paper/2506.05745/) (2025)
- [EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving](https://mlsanity.com/paper/2509.12603/) (2025)

## Built on by (most cited first, 11 of 11)

- [Test-time Recursive Thinking: Self-Improvement without External Feedback](https://mlsanity.com/paper/2602.03094/) (2026)
- [Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits](https://mlsanity.com/paper/2605.29268/) (2026)
- [Reliable Chain-of-Thought via Prefix Consistency](https://mlsanity.com/paper/2605.07654/) (2026)
- [When Does Delegation Beat Majority? A Delegation-Based Aggregator for Multi-Sample LLM Inference](https://mlsanity.com/paper/2606.08098/) (2026)
- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)
- [Deep Researcher with Sequential Plan Reflection and Candidates Crossover (Deep Researcher Reflect Evolve)](https://mlsanity.com/paper/2601.20843/) (2026)
- [Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B](https://mlsanity.com/paper/2607.28576/) (2026)
- [Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation](https://mlsanity.com/paper/2608.18379/) (2026)
- [Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models](https://mlsanity.com/paper/2608.25311/) (2026)
- [Measuring Collapse and Correction in Homogeneous-Panel LLM Debate](https://mlsanity.com/paper/2609.35279/) (2026)
- [Diversity Combining for Multi-Path LLM Reasoning](https://mlsanity.com/paper/2609.38829/) (2026)

## Abstract (arXiv)

We revisit test-time scaling for language model reasoning and ask a fundamental question: at equal token budget and compute, is it better to run multiple independent chains in parallel, or to run fewer chains that iteratively refine through sequential steps? Through comprehensive evaluation across 5 state-of-the-art open source models and 3 challenging reasoning benchmarks, we find that sequential scaling where chains explicitly build upon previous attempts consistently outperforms the dominant parallel self-consistency paradigm in 95.6% of configurations with gains in accuracy upto 46.7%. Further, we introduce inverse-entropy weighted voting, a novel training-free method to further boost the accuracy of sequential scaling. By weighing answers in proportion to the inverse entropy of their reasoning chains, we increase our success rate over parallel majority and establish it as the optimal test-time scaling strategy. Our findings fundamentally challenge the parallel reasoning orthodoxy that has dominated test-time scaling since Wang et al.'s self-consistency decoding (Wang et al., 2022), positioning sequential refinement as the robust default for modern LLM reasoning and necessitating a paradigm shift in how we approach inference-time optimization.