# Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency

arXiv: https://arxiv.org/abs/2509.13990 · HTML: https://mlsanity.com/paper/2509.13990/

## Key facts

- Cited by 13 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 40 references that are in the map.
- First posted on arXiv 17 Sep 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)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs](https://mlsanity.com/paper/2502.12134/) (2025)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning](https://mlsanity.com/paper/2505.17813/) (2025)
- [ServerlessLLM: Low-Latency Serverless Inference for Large Language Models](https://mlsanity.com/paper/2401.14351/) (2024)
- [The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models](https://mlsanity.com/paper/2401.05618/) (2024)
- [Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling](https://mlsanity.com/paper/2408.17017/) (2024)
- [Sampling-Efficient Test-Time Scaling: Self-Estimating the Best-of-N Sampling in Early Decoding](https://mlsanity.com/paper/2503.01422/) (2025)
- [SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning](https://mlsanity.com/paper/2505.11484/) (2025)
- [BLITZSCALE: Fast and Live Large Model Autoscaling with O(1) Host Caching](https://mlsanity.com/paper/2412.17246/) (2024)
- [Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning](https://mlsanity.com/paper/2502.00511/) (2025)
- [Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs](https://mlsanity.com/paper/2409.01281/) (2024)
- [Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction](https://mlsanity.com/paper/2508.20395/) (2025)

## Built on by (most cited first, 13 of 13)

- [Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing](https://mlsanity.com/paper/2602.03845/) (2026)
- [LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling](https://mlsanity.com/paper/2605.08083/) (2026)
- [ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation](https://mlsanity.com/paper/2601.02535/) (2026)
- [Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling](https://mlsanity.com/paper/2511.09345/) (2025)
- [MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement](https://mlsanity.com/paper/2512.07898/) (2025)
- [Intra-request branch orchestration for efficient LLM reasoning](https://mlsanity.com/paper/2509.24957/) (2025)
- [On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency](https://mlsanity.com/paper/2601.21619/) (2026)
- [Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees](https://mlsanity.com/paper/2604.20500/) (2026)
- [RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data](https://mlsanity.com/paper/2605.13775/) (2026)
- [ParaTempo: Efficient Parallel Reasoning via Temporal Confidence](https://mlsanity.com/paper/2608.16425/) (2026)
- [Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning](https://mlsanity.com/paper/2604.16029/) (2026)
- [Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning](https://mlsanity.com/paper/2608.15065/) (2026)
- [Frustratingly Easy Majority Voting Using Length Conditioning](https://mlsanity.com/paper/2610.19890/) (2026)

## Abstract (arXiv)

Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multiple reasoning chains in parallel and selects the final answer via majority voting. While effective, the order-of-magnitude computational overhead limits its broad deployment. Prior attempts to accelerate SC mainly rely on model-based confidence scores or heuristics with limited empirical support. For the first time, we theoretically and empirically analyze the inefficiencies of SC and reveal actionable opportunities for improvement. Building on these insights, we propose Slim-SC, a step-wise pruning strategy that identifies and removes redundant chains using inter-chain similarity at the thought level. Experiments on three STEM reasoning datasets and two recent LLM architectures show that Slim-SC reduces inference latency and KVC usage by up to 45% and 26%, respectively, with R1-Distill, while maintaining or improving accuracy, thus offering a simple yet efficient TTS alternative for SC.