# Self-Evaluating LLMs for Multi-Step Tasks: Stepwise Confidence Estimation for Failure Detection

arXiv: https://arxiv.org/abs/2511.07364 · HTML: https://mlsanity.com/paper/2511.07364/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 26 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [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)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Multi-hop Question Answering](https://mlsanity.com/paper/2204.09140/) (2022)
- [Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models](https://mlsanity.com/paper/2503.02623/) (2025)
- [Think Twice Before Trusting: Self-Detection for Large Language Models through Comprehensive Answer Reflection](https://mlsanity.com/paper/2403.09972/) (2024)
- [InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States](https://mlsanity.com/paper/2406.12053/) (2024)
- [Enhancing Confidence Expression in Large Language Models Through Learning from Past Experience](https://mlsanity.com/paper/2404.10315/) (2024)
- [Large Language Model Confidence Estimation via Black-Box Access](https://mlsanity.com/paper/2406.04370/) (2024)
- [Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences](https://mlsanity.com/paper/2502.01126/) (2025)
- [Graph-based Confidence Calibration for Large Language Models](https://mlsanity.com/paper/2411.02454/) (2024)
- [Reward Models Identify Consistency, Not Causality](https://mlsanity.com/paper/2502.14619/) (2025)
- [Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation](https://mlsanity.com/paper/2508.12040/) (2025)
- [Confidence Estimation for LLM-Based Dialogue State Tracking](https://mlsanity.com/paper/2409.09629/) (2024)

## Built on by (most cited first, 6 of 6)

- [Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents](https://mlsanity.com/paper/2607.12397/) (2026)
- [iFlip: Iterative Feedback-driven Counterfactual Example Refinement](https://mlsanity.com/paper/2601.01446/) (2026)
- [The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge](https://mlsanity.com/paper/2606.10296/) (2026)
- [Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM Debate](https://mlsanity.com/paper/2606.10307/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)
- [When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning](https://mlsanity.com/paper/2609.33220/) (2026)

## Abstract (arXiv)

Reliability and failure detection of large language models (LLMs) is critical for their deployment in high-stakes, multi-step reasoning tasks. Prior work explores confidence estimation for self-evaluating LLM-scorer systems, with confidence scorers estimating the likelihood of errors in LLM responses. However, most methods focus on single-step outputs and overlook the challenges of multi-step reasoning. In this work, we extend self-evaluation techniques to multi-step tasks, testing two intuitive approaches: holistic scoring and step-by-step scoring. Using two multi-step benchmark datasets, we show that stepwise evaluation generally outperforms holistic scoring in detecting potential errors, with up to 15% relative increase in AUC-ROC. Our findings demonstrate that self-evaluating LLM systems provide meaningful confidence estimates in complex reasoning, improving their trustworthiness and providing a practical framework for failure detection.