# MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools

arXiv: https://arxiv.org/abs/2504.20168 · HTML: https://mlsanity.com/paper/2504.20168/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 30 of 31)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding](https://mlsanity.com/paper/2404.16710/) (2024)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Reducing conversational agents' overconfidence through linguistic calibration](https://mlsanity.com/paper/2012.14983/) (2020)
- [Jump to Conclusions: Short-Cutting Transformers With Linear Transformations](https://mlsanity.com/paper/2303.09435/) (2023)
- [Calibration of Encoder Decoder Models for Neural Machine Translation](https://mlsanity.com/paper/1903.00802/) (2019)
- [Quantifying Differences in Reward Functions](https://mlsanity.com/paper/2006.13900/) (2020)
- [Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing](https://mlsanity.com/paper/2309.12236/) (2023)
- [On the Inference Calibration of Neural Machine Translation](https://mlsanity.com/paper/2005.00963/) (2020)
- [Calibrated Interpretation: Confidence Estimation in Semantic Parsing](https://mlsanity.com/paper/2211.07443/) (2022)
- [Can Unconditional Language Models Recover Arbitrary Sentences?](https://mlsanity.com/paper/1907.04944/) (2019)
- [Binary Classifier Calibration: Non-parametric approach](https://mlsanity.com/paper/1401.3390/) (2014)
- [BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing](https://mlsanity.com/paper/2206.10668/) (2022)
- [Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL](https://mlsanity.com/paper/2205.12422/) (2022)
- [Discovering Useful Sentence Representations from Large Pretrained Language Models](https://mlsanity.com/paper/2008.09049/) (2020)

## Built on by (most cited first, 15 of 15)

- [LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization](https://mlsanity.com/paper/2510.04013/) (2025)
- [REFLEX with Jev for Efficient Selective Control in LLM Agents](https://mlsanity.com/paper/2609.26532/) (2026)
- [SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone](https://mlsanity.com/paper/2510.17998/) (2025)
- [Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models](https://mlsanity.com/paper/2506.02132/) (2025)
- [Localized Calibrated Uncertainty in Code Language Models](https://mlsanity.com/paper/2512.24560/) (2025)
- [Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations](https://mlsanity.com/paper/2604.11322/) (2026)
- [Uncertainty Decomposition for Clarification Seeking in LLM Agents](https://mlsanity.com/paper/2606.19559/) (2026)
- [Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents](https://mlsanity.com/paper/2607.12397/) (2026)
- [The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust](https://mlsanity.com/paper/2606.07822/) (2026)
- [How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method](https://mlsanity.com/paper/2609.05274/) (2026)
- [Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents](https://mlsanity.com/paper/2605.28629/) (2026)
- [Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust](https://mlsanity.com/paper/2607.00083/) (2026)
- [Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations](https://mlsanity.com/paper/2609.09448/) (2026)
- [When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents](https://mlsanity.com/paper/2609.37153/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but prior work shows that many models are poorly calibrated. Inspired by interpretability literature exploring the internals of models, we propose a novel class of model-internal confidence estimators (MICE) to better assess confidence when calling tools. MICE first decodes from each intermediate layer of the language model using logitLens and then computes similarity scores between each layer's generation and the final output. These features are fed into a learned probabilistic classifier to assess confidence in the decoded output. On the simulated trial and error (STE) tool-calling dataset using Llama3 models, we find that MICE beats or matches the baselines on smoothed expected calibration error. Using MICE confidences to determine whether to call a tool significantly improves over strong baselines on a new metric, expected tool-calling utility. Further experiments show that MICE is sample-efficient, can generalize zero-shot to unseen APIs, and results in higher tool-calling utility in scenarios with varying risk levels. Our code is open source, available at https://github.com/microsoft/mice_for_cats.