Tag
This paper presents ERGO, an error-driven method for iterative prompt optimization in text classification that diagnoses classification failures and generates targeted decision rules, achieving best accuracy on tasks where errors concentrate in specific confused label pairs.
This paper formalizes Autonomous Agentic Data Engineering, where LLMs act as autonomous data engineers to curate and optimize training data for specialized domains, showing a 57.29% improvement in student model performance using GPT-5.2.
Introduces the autoresearch project, which breaks down the AI research process into a verifiable loop (fixed environment, single editable file, fixed metric, Git rollback), enabling AI agents to perform controllable and reproducible experiment iterations; also mentions the 12-factor-agents checklist.