# Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents

Source: [Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents](<https://www.sota2.com/research/paper/68fa7bab1e209131cea89c7a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:45:26.405Z

Authors: Jiaqi Shao, Yuxiang Lin, Munish Prasad Lohani, Yufeng Miao, Bing Luo

Published: 2025-09-26T14:18:50.000Z

## Abstract

Recent work has explored training Large Language Model (LLM) search agents with reinforcement learning (RL) for open-domain question answering (QA). However, most evaluations focus solely on final answer accuracy, overlooking how these agents reason with and act on external evidence. We introduce SeekBench, the first benchmark for evaluating the \\textit{epistemic competence} of LLM search agents through step-level analysis of their response traces. SeekBench comprises 190 expert-annotated traces with over 1,800 response steps generated by LLM search agents, each enriched with evidence annotations for granular analysis of whether agents (1) generate reasoning steps grounded in observed evidence, (2) adaptively reformulate searches to recover from low-quality results, and (3) have proper calibration to correctly assess whether the current evidence is sufficient for providing an answer.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.22391>)

[PDF](<https://arxiv.org/pdf/2509.22391.pdf>)
