# LLMs Encode Their Failures: Predicting Success from Pre-Generation Activations

arXiv: https://arxiv.org/abs/2602.09924 · HTML: https://mlsanity.com/paper/2602.09924/

## Key facts

- Cited by 14 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 20 of its 30 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## 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, 20 of 20)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [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)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)
- [MathArena: Evaluating LLMs on Uncontaminated Math Competitions](https://mlsanity.com/paper/2505.23281/) (2025)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response Theory](https://mlsanity.com/paper/2506.01048/) (2025)
- [No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes](https://mlsanity.com/paper/2509.10625/) (2025)
- [Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization](https://mlsanity.com/paper/2409.18433/) (2024)
- [Probing the Difficulty Perception Mechanism of Large Language Models](https://mlsanity.com/paper/2510.05969/) (2025)
- [LLMs Encode How Difficult Problems Are](https://mlsanity.com/paper/2510.18147/) (2025)

## Built on by (most cited first, 14 of 14)

- [Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities](https://mlsanity.com/paper/2603.10396/) (2026)
- [LLM Router: Rethinking Routing with Prefill Activations](https://mlsanity.com/paper/2603.20895/) (2026)
- [Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training](https://mlsanity.com/paper/2605.02241/) (2026)
- [Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs](https://mlsanity.com/paper/2606.27378/) (2026)
- [Future Confidence Distillation in Large Language Models](https://mlsanity.com/paper/2607.07626/) (2026)
- [Resample or Reroute? Recoverable Stopping Debt Without Identified Action Selection](https://mlsanity.com/paper/2607.08665/) (2026)
- [On the Robustness of LLMs' Internal Representation of Code Correctness](https://mlsanity.com/paper/2608.08266/) (2026)
- [It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories](https://mlsanity.com/paper/2609.03436/) (2026)
- [Dynamic LLM Routers are Often Misguided](https://mlsanity.com/paper/2610.02762/) (2026)
- [HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment](https://mlsanity.com/paper/2609.38006/) (2026)
- [Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing](https://mlsanity.com/paper/2610.06216/) (2026)
- [From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations](https://mlsanity.com/paper/2610.15412/) (2026)
- [Structural Baselines Matter for Agent Failure Detection and Attribution](https://mlsanity.com/paper/2610.16661/) (2026)
- [Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization](https://mlsanity.com/paper/2610.19198/) (2026)

## Abstract (arXiv)

Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We investigate whether their own likelihood of success is recoverable from their internal representations before generation, and if this signal can guide more efficient inference. We train linear probes on pre-generation activations to predict policy-specific success on math and coding tasks, substantially outperforming surface features such as question length and TF-IDF. Using E2H-AMC, which provides both human and model performance on identical problems, we show that models encode a model-specific notion of difficulty that is distinct from human difficulty, and that this distinction increases with extended reasoning. Leveraging these probes, we demonstrate that routing queries across a pool of models can exceed the best-performing model whilst reducing inference cost by up to 70% on MATH, showing that internal representations enable practical efficiency gains even when they diverge from human intuitions about difficulty. Our code is available at: https://github.com/KabakaWilliam/llmsknowdifficulty