# Entropy-Gated Branching for Efficient Test-Time Reasoning

arXiv: https://arxiv.org/abs/2503.21961 · HTML: https://mlsanity.com/paper/2503.21961/

## Key facts

- Cited by 22 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 30 of its 56 references that are in the map.
- First posted on arXiv 27 Mar 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, 30 of 30)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [Planning with Large Language Models for Code Generation](https://mlsanity.com/paper/2303.05510/) (2023)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling](https://mlsanity.com/paper/2502.06703/) (2025)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning](https://mlsanity.com/paper/2403.20046/) (2024)
- [Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks](https://mlsanity.com/paper/2305.05862/) (2023)
- [Importance of Search and Evaluation Strategies in Neural Dialogue Modeling](https://mlsanity.com/paper/1811.00907/) (2018)
- [Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification](https://mlsanity.com/paper/2410.05318/) (2024)
- [Are Large Language Models Good Prompt Optimizers?](https://mlsanity.com/paper/2402.02101/) (2024)
- [A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks](https://mlsanity.com/paper/2501.10069/) (2025)
- [Black-box Uncertainty Quantification Method for LLM-as-a-Judge](https://mlsanity.com/paper/2410.11594/) (2024)
- [What's Wrong? Refining Meeting Summaries with LLM Feedback](https://mlsanity.com/paper/2407.11919/) (2024)
- [Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy](https://mlsanity.com/paper/2503.00269/) (2025)

## Built on by (most cited first, 22 of 22)

- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning](https://mlsanity.com/paper/2508.06924/) (2025)
- [The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute](https://mlsanity.com/paper/2511.02309/) (2025)
- [Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning](https://mlsanity.com/paper/2602.18232/) (2026)
- [Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention](https://mlsanity.com/paper/2510.13940/) (2025)
- [Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation](https://mlsanity.com/paper/2506.06971/) (2025)
- [Rethinking Code Complexity Through the Lens of Large Language Models](https://mlsanity.com/paper/2602.07882/) (2026)
- [Code Is More Than Text: Uncertainty Estimation for Code Generation](https://mlsanity.com/paper/2606.09577/) (2026)
- [Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search](https://mlsanity.com/paper/2509.25835/) (2025)
- [Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching](https://mlsanity.com/paper/2604.12126/) (2026)
- [Dissecting Failure Dynamics in Large Language Model Reasoning](https://mlsanity.com/paper/2604.14528/) (2026)
- [Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models](https://mlsanity.com/paper/2602.15332/) (2026)
- [From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning](https://mlsanity.com/paper/2605.12944/) (2026)
- [Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning](https://mlsanity.com/paper/2605.19358/) (2026)
- [ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling](https://mlsanity.com/paper/2605.26172/) (2026)
- [What Am I Missing? Question-Answering as Hidden State Probing](https://mlsanity.com/paper/2605.31561/) (2026)
- [Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning](https://mlsanity.com/paper/2602.02427/) (2026)
- [Entropy-informed Decoding: Adaptive Information-Driven Branching](https://mlsanity.com/paper/2605.09745/) (2026)
- [Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models](https://mlsanity.com/paper/2606.04396/) (2026)
- [Entropy-Gated Latent Recursion](https://mlsanity.com/paper/2606.16620/) (2026)
- [On the Diversity of Analogy Making in Large Language Models](https://mlsanity.com/paper/2608.03233/) (2026)
- [Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering](https://mlsanity.com/paper/2610.02391/) (2026)

## Abstract (arXiv)

Test-time compute methods can significantly improve the reasoning capabilities and problem-solving accuracy of large language models (LLMs). However, these approaches require substantially more computational resources, with most compute wasted on exploring low-diversity branches where the model already exhibits high confidence. We observe that a small subset of uncertain reasoning steps has a disproportionately large impact on final prediction accuracy, and branching at these critical junctures tends to yield more diverse and higher-quality candidate reasoning steps. We propose Entropy-Gated Branching (EGB), which branches only at high-uncertainty steps and prunes expansions with a lightweight verifier. On mathematical and financial reasoning benchmarks, EGB improves accuracy by 22.6% over standard inference while operating 31%-75% faster across math benchmarks than test-time beam search with higher performance. Our results show that dynamic resource allocation during inference can substantially improve both efficiency and effectiveness, offering a more scalable pathway to enhanced LLM reasoning capabilities.