ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
- BenchAgents: Multi-Agent Systems for Structured Benchmark Creation
- Automated Benchmark Generation from Domain Guidelines Informed by Bloom's Taxonomy
- BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models
- ProbeLLM: Automating Principled Diagnosis of LLM Failures
- Anchor: Mitigating Artifact Drift in Agent Benchmark Generation
- Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction
- AI Evaluation Should Require Standardized Item-Level Data Releases
- ChartGen: Scaling Chart Understanding Via Code-Guided Synthetic Chart Generation
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
- Targeted Tests for LLM Reasoning: An Audit-Constrained Protocol
- ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation
- ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch
- LEVER: Learning to Verify Language-to-Code Generation with Execution
- PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems
- RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator
- Large Language Models are not Fair Evaluators
- CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems