Tag
A DeepSeek researcher open-sourced AutoResearch, an autonomous framework that can plan, execute, and debug RL experiments on the DeepSeek 285B model without human intervention, accompanied by a self-play survey paper.
Deli AutoResearch SKILL is open-sourced, an autonomous framework that automates GPU experiments and RL pipelines, with a companion survey paper on Self-play.
MOSAIC introduces a structured agentic framework for automated data science that uses memory-grounded model selection and workflow construction, validated on financial time-series tasks. It outperforms AutoML and agentic baselines.
CANTANTE is an open-source framework that solves the credit assignment problem in multi-agent systems by converting system-level rewards into per-agent update signals, outperforming DSPy-based baselines on coding and math reasoning benchmarks.