AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/StarDewXXX/AutoDataBench
Sources
- BenchAgents: Multi-Agent Systems for Structured Benchmark Creation
- MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- Environment Evolution for Terminal Agents
- Learning to Reason at the Frontier of Learnability
- Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation
- Prioritized Level Replay
- Towards Active Synthetic Data Generation for Finetuning Language Models
- AutoBencher: Towards Declarative Benchmark Construction
- RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
- PostTrainBench: Can LLM Agents Automate LLM Post-Training?
- Self-Improvements in Modern Agentic Systems: A Survey
- AutomationBench
- TaskCraft: Automated Generation of Agentic Tasks
- Self-Instruct: Aligning Language Models with Self-Generated Instructions
- RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
- InnovatorBench: Evaluating Agents' Ability to Conduct Innovative LLM Research
- SWE-smith: Scaling Data for Software Engineering Agents
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