Agent Benchmarks Fail Public Sector Requirements

• URL: http://arxiv.org/abs/2601.20617v1
• Date: Wed, 28 Jan 2026 13:51:30 GMT
• Title: Agent Benchmarks Fail Public Sector Requirements
• Abstract summary: It remains unclear what criteria benchmarks must meet to ensure they adequately reflect public-sector requirements.<n>We first define such criteria based on a first-principles survey of public administration literature.<n>We analyse more than 1,300 benchmark papers for these criteria using an expert-validated LLM-assisted pipeline.
• Score: 4.1796836971711055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deploying Large Language Model-based agents (LLM agents) in the public sector requires assuring that they meet the stringent legal, procedural, and structural requirements of public-sector institutions. Practitioners and researchers often turn to benchmarks for such assessments. However, it remains unclear what criteria benchmarks must meet to ensure they adequately reflect public-sector requirements, or how many existing benchmarks do so. In this paper, we first define such criteria based on a first-principles survey of public administration literature: benchmarks must be \emph{process-based}, \emph{realistic}, \emph{public-sector-specific} and report \emph{metrics} that reflect the unique requirements of the public sector. We analyse more than 1,300 benchmark papers for these criteria using an expert-validated LLM-assisted pipeline. Our results show that no single benchmark meets all of the criteria. Our findings provide a call to action for both researchers to develop public sector-relevant benchmarks and for public-sector officials to apply these criteria when evaluating their own agentic use cases.

Related papers

• GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation [74.44235943118994]
  GenRubric is a self-evolving framework that improves rubric generation from unlabeled queries.<n>We implement this principle through reinforcement learning, combining a cross-rubric comprehensiveness signal with group-level and criterion-level rewards for rubric quality.<n> Experiments on human-annotated rubric benchmarks show that self-evolution improves the agreement between evaluations induced by generated rubrics and those induced by expert-written rubrics.
  arXiv  Detail & Related papers  (2026-08-30T15:39:39Z)
• PACE: A Proxy for Agentic Capability Evaluation [60.3743414796937]
  We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations.<n>Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80, and pairwise model-ranking accuracy around 85%, all at much less than 1% of the full agentic evaluation cost.
  arXiv  Detail & Related papers  (2026-07-02T10:59:03Z)
• Benchmark Everything Everywhere All at Once [28.30618112297148]
  We introduce Benchmark Agent, a fully autonomous agentic system designed for benchmark building.<n>Our framework orchestrates the complete benchmark construction pipeline, from user query analysis and subtask design to data annotation and quality control.<n>We produce 15 representative benchmarks, spanning diverse evaluation scenarios, including text understanding, multimodal understanding, and domain-specific reasoning.
  arXiv  Detail & Related papers  (2026-06-04T17:52:04Z)
• The Necessity of a Unified Framework for LLM-Based Agent Evaluation [46.631678638677386]
  General-purpose agents have seen fundamental advancements.<n> evaluating these agents presents unique challenges that distinguish them from static QA benchmarks.<n>We propose that a unified evaluation framework is essential for the rigorous advancement of agent evaluation.
  arXiv  Detail & Related papers  (2026-02-03T08:18:37Z)
• Expert Preference-based Evaluation of Automated Related Work Generation [54.29459509574242]
  We propose GREP, a multi-turn evaluation framework that integrates classical related work evaluation criteria with expert-specific preferences.<n>For better accessibility, we design two variants of GREP: a more precise variant with proprietary LLMs as evaluators, and a cheaper alternative with open-weight LLMs.
  arXiv  Detail & Related papers  (2025-08-11T13:08:07Z)
• Deprecating Benchmarks: Criteria and Framework [2.6449913368815516]
  We propose criteria to decide when to fully or partially deprecate benchmarks, and a framework for deprecating benchmarks.<n>Our work aims to advance the state of benchmarking towards rigorous and quality evaluations, especially for frontier models.
  arXiv  Detail & Related papers  (2025-07-08T22:29:06Z)
• Establishing Best Practices for Building Rigorous Agentic Benchmarks [94.69724201080155]
  We show that many agentic benchmarks have issues in task setup or reward design.<n>Such issues can lead to under- or overestimation of agents' performance by up to 100% in relative terms.<n>We introduce the Agentic Benchmark Checklist (ABC), a set of guidelines that we synthesized from our benchmark-building experience.
  arXiv  Detail & Related papers  (2025-07-03T17:35:31Z)
• Social Bias in Popular Question-Answering Benchmarks [0.0]
  Question-answering (QA) and reading comprehension (RC) benchmarks are essential for assessing the capabilities of large language models (LLMs) in retrieving and reproducing knowledge.<n>We demonstrate that popular QA and RC benchmarks are biased and do not cover questions about different demographics or regions in a representative way.
  arXiv  Detail & Related papers  (2025-05-21T14:14:47Z)
• EvalAgent: Discovering Implicit Evaluation Criteria from the Web [82.82096383262068]
  We introduce EvalAgent, a framework designed to automatically uncover nuanced and task-specific criteria.<n>EvalAgent mines expert-authored online guidance to propose diverse, long-tail evaluation criteria.<n>Our experiments demonstrate that the grounded criteria produced by EvalAgent are often implicit, yet specific.
  arXiv  Detail & Related papers  (2025-04-21T16:43:50Z)
• More than Marketing? On the Information Value of AI Benchmarks for Practitioners [42.73526862595375]
  In academia, public benchmarks were generally viewed as suitable measures for capturing research progress.<n>In product and policy, benchmarks were often found to be inadequate for informing substantive decisions.<n>We conclude that effective benchmarks should provide meaningful, real-world evaluations, incorporate domain expertise, and maintain transparency in scope and goals.
  arXiv  Detail & Related papers  (2024-12-07T03:35:39Z)
• The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models [94.31327813151208]
  BiGGen Bench is a principled generation benchmark designed to thoroughly evaluate nine distinct capabilities of LMs across 77 diverse tasks.<n>A key feature of the BiGGen Bench is its use of instance-specific evaluation criteria, closely mirroring the nuanced discernment of human evaluation.
  arXiv  Detail & Related papers  (2024-06-09T12:30:30Z)
• HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition [92.17397504834825]
  HD-Eval is a framework that iteratively aligns large language models evaluators with human preference. HD-Eval inherits the essence from the evaluation mindset of human experts and enhances the alignment of LLM-based evaluators. Extensive experiments on three evaluation domains demonstrate the superiority of HD-Eval in further aligning state-of-the-art evaluators.
  arXiv  Detail & Related papers  (2024-02-24T08:01:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.