# ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models

arXiv: https://arxiv.org/abs/2511.06209 · HTML: https://mlsanity.com/paper/2511.06209/

## Key facts

- Cited by 10 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 19 of its 55 references that are in the map.
- First posted on arXiv 9 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, 19 of 19)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [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)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [The Lessons of Developing Process Reward Models in Mathematical Reasoning](https://mlsanity.com/paper/2501.07301/) (2025)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [ProofNet: Autoformalizing and Formally Proving Undergraduate-Level Mathematics](https://mlsanity.com/paper/2302.12433/) (2023)
- [Phi-4-reasoning Technical Report](https://mlsanity.com/paper/2504.21318/) (2025)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [StepWiser: Stepwise Generative Judges for Wiser Reasoning](https://mlsanity.com/paper/2508.19229/) (2025)
- [MUR: Momentum Uncertainty guided Reasoning for Large Language Models](https://mlsanity.com/paper/2507.14958/) (2025)
- [StepProof: Step-by-step verification of natural language mathematical proofs](https://mlsanity.com/paper/2506.10558/) (2025)
- [Step-Wise Formal Verification for LLM-Based Mathematical Problem Solving](https://mlsanity.com/paper/2505.20869/) (2025)

## Built on by (most cited first, 10 of 10)

- [ReDAct: Uncertainty-Aware Deferral for LLM Agents](https://mlsanity.com/paper/2604.07036/) (2026)
- [CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute](https://mlsanity.com/paper/2602.08948/) (2026)
- [Learning When to Sample: Confidence-Aware Selective Sampling for Efficient Chain-of-Thought Reasoning](https://mlsanity.com/paper/2603.08999/) (2026)
- [Trust or Abstain? A Self-Aware RAG Approach](https://mlsanity.com/paper/2605.18792/) (2026)
- [ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning](https://mlsanity.com/paper/2606.06915/) (2026)
- [Mitigating LLM Sycophancy in Code Smell Detection Using Evidence-Guided Reasoning Prompts](https://mlsanity.com/paper/2607.10411/) (2026)
- [Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software Agents](https://mlsanity.com/paper/2608.22191/) (2026)
- [From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts](https://mlsanity.com/paper/2609.06403/) (2026)
- [Attention-Graph Curvature for the Verification of Mathematical Reasoning](https://mlsanity.com/paper/2610.16709/) (2026)
- [Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference](https://mlsanity.com/paper/2610.20292/) (2026)

## Abstract (arXiv)

LLMs can solve complex tasks by generating long, multi-step reasoning chains. Test-time scaling (TTS) can further improve performance by sampling multiple variants of intermediate reasoning steps, verifying their correctness, and selecting the best steps for continuation. However, existing verification approaches, such as Process Reward Models (PRMs), are computationally expensive and require large-scale human or model-generated annotations. We propose a lightweight alternative for step-level reasoning verification based on probing the internal states of LLMs. We train a transformer-based probe that uses the internal states of a frozen LLM to estimate the credibility of its reasoning steps during generation. Annotation can be provided either by a larger LLM (e.g., DeepSeek-R1) or in a self-supervised manner by the original model itself. The probes are lightweight, containing fewer than 10M parameters. Across multiple domains, including mathematics, planning, and general knowledge question answering, our probes match or exceed the performance of PRMs that are up to 810x larger. These results suggest that LLM internal states encode confidence in their reasoning processes and can serve as reliable signals for step verification, offering a promising path toward scalable, generalizable TTS and more introspective LLMs.