Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration
This addresses the issue of misleading information in open-ended research scenarios for users relying on automated report generation, though it appears incremental as it builds on existing agent-based systems.
The paper tackles the problem of evaluating trustworthiness in deep research agents that generate reports, proposing a system with progressive confidence estimation and calibration to improve transparency and user trust.
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.