# Agentic Confidence Calibration

arXiv: https://arxiv.org/abs/2601.15778 · HTML: https://mlsanity.com/paper/2601.15778/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 41 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [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)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [A Survey of Confidence Estimation and Calibration in Large Language Models](https://mlsanity.com/paper/2311.08298/) (2023)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [Large-scale Simple Question Answering with Memory Networks](https://mlsanity.com/paper/1506.02075/) (2015)

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

- [Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management](https://mlsanity.com/paper/2605.06472/) (2026)
- [AI-Assisted Engineering Should Track the Epistemic Status and Temporal Validity of Architectural Decisions](https://mlsanity.com/paper/2601.21116/) (2026)
- [Uncertainty Propagation in LLM-Based Systems](https://mlsanity.com/paper/2604.23505/) (2026)
- [Calibration Is Not Control: Why LLM-Agent Oversight Needs Intervention](https://mlsanity.com/paper/2606.21399/) (2026)
- [Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents](https://mlsanity.com/paper/2608.29685/) (2026)
- [Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier](https://mlsanity.com/paper/2606.20662/) (2026)
- [How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method](https://mlsanity.com/paper/2609.05274/) (2026)
- [One Human, N Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence](https://mlsanity.com/paper/2607.28317/) (2026)
- [DualStake: Dual-Path Confidence Calibration in Deep Research Agents](https://mlsanity.com/paper/2609.00935/) (2026)
- [Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study](https://mlsanity.com/paper/2609.07395/) (2026)
- [Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations](https://mlsanity.com/paper/2609.09448/) (2026)
- [GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes](https://mlsanity.com/paper/2609.24831/) (2026)
- [Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races](https://mlsanity.com/paper/2609.29522/) (2026)
- [Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps](https://mlsanity.com/paper/2610.02740/) (2026)
- [Agentic Self-Awareness: Aligning Knowing, Acting, and Holding](https://mlsanity.com/paper/2610.19226/) (2026)

## Abstract (arXiv)

AI agents are rapidly advancing from passive language models to autonomous systems executing complex, multi-step tasks. Yet their overconfidence in failure remains a fundamental barrier to deployment in high-stakes settings. Existing calibration methods, built for static single-turn outputs, cannot address the unique challenges of agentic systems, such as compounding errors along trajectories, uncertainty from external tools, and opaque failure modes. To address these challenges, we introduce, for the first time, the problem of Agentic Confidence Calibration and propose Holistic Trajectory Calibration (HTC), a novel diagnostic framework that extracts rich process-level features ranging from macro dynamics to micro stability across an agent's entire trajectory. Powered by a simple, interpretable model, HTC consistently surpasses strong baselines in both calibration and discrimination, across eight benchmarks, multiple LLMs, and diverse agent frameworks. Beyond performance, HTC delivers three essential advances: it provides interpretability by revealing the signals behind failure, enables transferability by applying across domains without retraining, and achieves generalization through a General Agent Calibrator (GAC) that achieves the best calibration (lowest ECE) on the out-of-domain GAIA benchmark. Together, these contributions establish a new process-centric paradigm for confidence calibration, providing a framework for diagnosing and enhancing the reliability of AI agents.