Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

• URL: http://arxiv.org/abs/2605.30916v1
• Date: Fri, 29 May 2026 07:01:38 GMT
• Title: Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
• Abstract summary: We model benchmarking as a multitask principal-agent game and show that the welfare loss from a benchmark is determined jointly by three item-level primitives.<n>We apply the theory to OLMES items using WORKBank for welfare, the EvoLM 4B suite for improvability, and the PolyPythias 410M panel for variance.
• Score: 19.980368400366352
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention: benchmarks are typically summarized by uniformly averaging item-level scores, implicitly treating every test item as equally valuable. We model benchmarking as a multitask principal-agent game and show that the welfare loss from a benchmark is determined jointly by three item-level primitives: alignment with normative welfare priorities, marginal improvability, and performance variance. We translate the theory into an audit framework that ranks items along each of these three axes, and apply it to OLMES items using WORKBank for welfare, the EvoLM 4B suite for improvability, and the PolyPythias 410M panel for variance. The framework surfaces items that are Pareto-inferior within OLMES subject to a pro-worker welfare operationalization. All code is available at https://github.com/stair-lab/principal-agent-benchmarks.

Related papers

• 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)
• Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents [19.290397279235084]
  This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date.<n>We argue that aggregate-score leaderboards systematically underspecify deployed-agent evaluation.
  arXiv  Detail & Related papers  (2026-06-18T02:02:46Z)
• 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)
• A Unified Framework for the Evaluation of LLM Agentic Capabilities [36.43241368835721]
  We present a unified framework for the fair evaluation of LLM agentic capabilities.<n> Driven by a unified configuration system, the framework integrates diverse benchmarks into a standardized instruction--tool--environment format.<n>We conduct a large-scale empirical analysis over 400K rollouts and 5B tokens on 15 models.
  arXiv  Detail & Related papers  (2026-05-27T03:20:45Z)
• Position: State-of-the-Art Claims Require State-of-the-Art Evidence [7.225436467899107]
  State-of-the-Art (SOTA) claims pervade Artificial Intelligence (AI) and Machine Learning (ML) research.<n>These claims rest on benchmark evaluations, where models are ranked by aggregate scores across tasks.<n>We identify a widespread claim-evidence gap in AI benchmarking.<n>We argue that claim language should reflect the strength of the underlying evidence.
  arXiv  Detail & Related papers  (2026-05-17T05:48:10Z)
• Agent psychometrics: Task-level performance prediction in agentic coding benchmarks [24.348135523715815]
  We present a framework for predicting success or failure on individual tasks tailored to the agentic coding regime.<n>Our approach augments Item Response Theory (IRT) with rich features extracted from tasks, including issue statements, repository contexts, solutions, and test cases.
  arXiv  Detail & Related papers  (2026-04-01T07:59:59Z)
• Benchmarking at the Edge of Comprehension [38.43582342860192]
  If benchmarking becomes infeasible, our ability to measure any progress in AI is at stake.<n>We propose Critique-Resilient Benchmarking, an adversarial framework designed to compare models even when full human understanding is infeasible.<n>Unlike standard benchmarking, humans serve as bounded verifiers and focus on localized claims.
  arXiv  Detail & Related papers  (2026-02-15T20:51:29Z)
• Structured Prompting Enables More Robust Evaluation of Language Models [38.53918044830268]
  We present a DSPy+HELM framework that introduces structured prompting methods which elicit reasoning.<n>We find that without structured prompting, HELM underestimates LM performance (by 4% average) and performance estimates vary more across benchmarks.<n>This is the first benchmarking study to systematically integrate structured prompting into an established evaluation framework.
  arXiv  Detail & Related papers  (2025-11-25T20:37:59Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks [34.09939383415074]
  Benchmark Profiling decomposes benchmark performance into ten cognitively grounded abilities.<n>It explains why performance gains do not always translate into user-perceived competence.
  arXiv  Detail & Related papers  (2025-09-23T15:32:47Z)
• Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling [83.78874399606379]
  We propose MACT, a Multi-Agent Collaboration framework with Test-Time scaling.<n>It comprises four distinct small-scale agents, with clearly defined roles and effective collaboration.<n>It shows superior performance with a smaller parameter scale without sacrificing the ability of general and mathematical tasks.
  arXiv  Detail & Related papers  (2025-08-05T12:52:09Z)
• 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)
• carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks [61.79411281702448]
  carps is a benchmark framework for Comprehensive Automated Research Performance Studies.<n>We focus on the four most important types of HPO task types: blackbox, multi-objective, multi-fidelity-multi-objective.<n>With 3 336 tasks from 5 community benchmark collections and 28 variants of 9 families, we offer the biggest go-to library to date.
  arXiv  Detail & Related papers  (2025-06-06T15:01:39Z)
• The Benchmark Lottery [114.43978017484893]
  "A benchmark lottery" describes the overall fragility of the machine learning benchmarking process. We show that the relative performance of algorithms may be altered significantly simply by choosing different benchmark tasks.
  arXiv  Detail & Related papers  (2021-07-14T21:08:30Z)

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.