# Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration

arXiv: https://arxiv.org/abs/2604.05952 · HTML: https://mlsanity.com/paper/2604.05952/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 27 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 21 of 21)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations](https://mlsanity.com/paper/2506.13651/) (2025)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools](https://mlsanity.com/paper/2502.04644/) (2025)
- [On Verbalized Confidence Scores for LLMs](https://mlsanity.com/paper/2412.14737/) (2024)
- [Calibrating Large Language Models with Sample Consistency](https://mlsanity.com/paper/2402.13904/) (2024)
- [A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges](https://mlsanity.com/paper/2508.05668/) (2025)
- [DSformer: A Double Sampling Transformer for Multivariate Time Series Long-term Prediction](https://mlsanity.com/paper/2308.03274/) (2023)
- [Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator](https://mlsanity.com/paper/2505.16690/) (2025)
- [Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges](https://mlsanity.com/paper/2506.10408/) (2025)
- [QA-Calibration of Language Model Confidence Scores](https://mlsanity.com/paper/2410.06615/) (2024)
- [On the Calibration of Multilingual Question Answering LLMs](https://mlsanity.com/paper/2311.08669/) (2023)
- [On using Machine Learning Algorithms for Motorcycle Collision Detection](https://mlsanity.com/paper/2403.09491/) (2024)

## Built on by (most cited first, 1 of 1)

- [BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery](https://mlsanity.com/paper/2606.20997/) (2026)

## Abstract (arXiv)

As agent-based systems continue to evolve, deep research agents are capable of automatically generating research-style reports across diverse domains. While these agents promise to streamline information synthesis and knowledge exploration, existing evaluation frameworks-typically based on subjective dimensions-fail to capture a critical aspect of report quality: trustworthiness. In open-ended research scenarios where ground-truth answers are unavailable, current evaluation methods cannot effectively measure the epistemic confidence of generated content, making calibration difficult and leaving users susceptible to misleading or hallucinated information. To address this limitation, we propose a novel deep research agent that incorporates progressive confidence estimation and calibration within the report generation pipeline. Our system leverages a deliberative search model, featuring deep retrieval and multi-hop reasoning to ground outputs in verifiable evidence while assigning confidence scores to individual claims. Combined with a carefully designed workflow, this approach produces trustworthy reports with enhanced transparency. Experimental results and case studies demonstrate that our method substantially improves interpretability and significantly increases user trust.