Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility

• URL: http://arxiv.org/abs/2605.06856v2
• Date: Mon, 11 May 2026 17:22:01 GMT
• Title: Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
• Abstract summary: We argue that generative AI evaluation requires a paradigm shift from static benchmark-centered transparency toward stakeholder, goal, and context-conditioned utility transparency grounded in human outcome trajectories.<n>We propose SCU-GenEval, a four-stage evaluation framework consisting of stakeholder-goal mapping, construct-indicator specification, mechanism modeling, and longitudinal utility measurement.
• Score: 9.928824688627037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI systems achieve impressive performance on standard benchmarks yet fail to deliver real-world utility, a disconnect we identify across 28 deployment cases spanning education, healthcare, software engineering, and law. We argue that this benchmark utility gap arises from three recurring failures in evaluation practice: proxy displacement, temporal collapse, and distributional concealment. Motivated by these observations, we argue that generative AI evaluation requires a paradigm shift from static benchmark-centered transparency toward stakeholder, goal, and context-conditioned utility transparency grounded in human outcome trajectories. Existing evaluations primarily characterize properties of model outputs, while deployment success depends on whether interaction with AI improves stakeholders' ability to achieve their goals over time. The missing construct is therefore utility: the change in a stakeholder's capability induced through sustained interaction with an AI system within a deployment context. To operationalize this perspective, we propose SCU-GenEval, a four-stage evaluation framework consisting of stakeholder-goal mapping, construct-indicator specification, mechanism modeling, and longitudinal utility measurement. To make these stages practically deployable, we introduce three supporting instruments: structured deployment protocols, context-conditioned user simulators, and persona- and goal-conditioned proxy metrics. We conclude with domain-specific calls to action, arguing that progress in generative AI must be evaluated through measurable improvements in human outcomes rather than benchmark performance alone.

Related papers

• The Evaluation Context Protocol (ECP): A Portable Contract for AI Agent Evaluation [0.0]
  This paper explores the critical methodologies for evaluating AI agents and the essential role of advanced observability infrastructure.<n>We propose the Evaluation Context Protocol (ECP), an early-stage, vendor-neutral framework intended to act as a contract layer for agentic systems.<n>We describe an open-source reference implementation that includes adapters for LangChain, LlamaIndex, CrewAI, and PydanticAI.
  arXiv  Detail & Related papers  (2026-08-18T07:14:36Z)
• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities [55.23913617185508]
  Agent is an open-source, lightweight, and infrastructure for evaluating Large Language Models (LLMs)-based agents.<n>It organizes the evaluation process around three independent components, namely Benchmark, Harness and Environment.<n>It features a fault-tolerant runtime and comprehensive trajectory analysis tools to transparently diagnose failure modes like reward-hacking.
  arXiv  Detail & Related papers  (2026-07-15T11:11:17Z)
• From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape [79.30826980815927]
  rubrics are explicit criteria sets that transform complex quality judgments into structured and actionable standards.<n>We systematically organize existing rubric designs, examine their construction and optimization, and analyze their role across evaluation and training.
  arXiv  Detail & Related papers  (2026-06-07T13:34:55Z)
• Interactive Evaluation Requires a Design Science [90.62695599188204]
  Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents.<n>The field has begun to build interactive benchmarks, but the resulting landscape is fragmented.<n>This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm.
  arXiv  Detail & Related papers  (2026-05-18T04:03:18Z)
• Measuring the Machine: Evaluating Generative AI as Pluralist Sociotechical Systems [0.0]
  The thesis argues that generative AI must be evaluated as a pluralist sociotechnical system.<n>MaSH Loops is a framework for tracing how models, users, and institutions co-construct meaning and values.<n>The World Values Benchmark introduces a distributional approach grounded in World Values Survey data.
  arXiv  Detail & Related papers  (2026-04-22T13:29:33Z)
• ManipArena: Comprehensive Real-world Evaluation of Reasoning-Oriented Generalist Robot Manipulation [66.02142169323521]
  Vision-Language-Action models and world models have recently emerged as promising paradigms for general-purpose robotic intelligence.<n>Existing benchmarks are largely simulator-centric, which provide controllability but fail to capture the reality gap caused by perception noise.<n>We introduce ManipArena, a standardized evaluation framework designed to bridge simulation and real-world execution.
  arXiv  Detail & Related papers  (2026-03-30T15:06:41Z)
• UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities [70.79422099851506]
  We present UniDial-EvalKit (UDE), a unified evaluation toolkit for assessing interactive AI systems.<n>UDE standardizes heterogeneous data formats into a universal schema, streamlines complex evaluation pipelines through a modular architecture, and aligns metric calculations under a consistent scoring interface.
  arXiv  Detail & Related papers  (2026-03-24T13:01:31Z)
• Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models [7.802379200026965]
  We propose an adaptive framework that dynamically routes VLA execution based on the complexity of the perceived state.<n>Our approach transforms the VLA's vision-language backbone into an active detection tool by projecting latent embeddings into an ensemble of parametric and non-parametric estimators.
  arXiv  Detail & Related papers  (2026-03-05T13:14:41Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Trustworthy Evaluation of Robotic Manipulation: A New Benchmark and AutoEval Methods [30.612032540735402]
  We propose a solution that combines the Eval-Actions benchmark and the AutoEval architecture.<n>This dataset is structured around three core supervision signals: Expert Grading (EG), Rank-Guided preferences (RG), and Chain-of-Thought (CoT)<n>Experiments show AutoEval achieves Spearman's Rank Correlation Coefficients (SRCC) of 0.81 and 0.84 under the EG and RG protocols, respectively.
  arXiv  Detail & Related papers  (2026-01-26T17:47:42Z)
• The Geometry of Benchmarks: A New Path Toward AGI [0.0]
  We introduce a geometric framework in which all psychometric batteries for AI agents are treated as points in a structured moduli space.<n>First, we define an Autonomous AI (AAI) Scale, a Kardashev-style hierarchy of autonomy grounded in measurable performance.<n>Second, we construct a moduli space of batteries, identifying equivalence classes of benchmarks that are indistinguishable at the level of agent orderings and capability inferences.<n>Third, we introduce a general Generator-Verifier-Updater (GVU) operator that subsumes reinforcement learning, self-play, debate and verifier-based fine-tuning
  arXiv  Detail & Related papers  (2025-12-03T21:34:09Z)
• RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark [71.3555284685426]
  We introduce RealUnify, a benchmark designed to evaluate bidirectional capability synergy.<n>RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks.<n>We find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient.
  arXiv  Detail & Related papers  (2025-09-29T15:07:28Z)
• Adapting Vision-Language Models for Evaluating World Models [24.813041196394582]
  We present UNIVERSE, a method for adapting Vision-language Evaluator for Rollouts in Simulated Environments under data and compute constraints.<n>We conduct a large-scale study comparing full, partial, and parameter-efficient finetuning across task formats, context lengths, sampling strategies, and data compositions.<n>The resulting unified evaluator matches the performance of task-specific baselines using a single checkpoint.
  arXiv  Detail & Related papers  (2025-06-22T09:53:28Z)
• Benchmarks as Microscopes: A Call for Model Metrology [76.64402390208576]
  Modern language models (LMs) pose a new challenge in capability assessment. To be confident in our metrics, we need a new discipline of model metrology.
  arXiv  Detail & Related papers  (2024-07-22T17:52:12Z)

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.