MARS is a modular agent framework that achieves state-of-the-art results on MLE-Bench among open-source systems by combining budget-aware MCTS planning, a Design-Decompose-Implement pipeline, and comparative reflective memory for cross-branch insight transfer.
- Imbalance/Skew: - If Classification: Calculate class balance ratios
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MARS: Modular Agent with Reflective Search for Automated AI Research
MARS is a modular agent framework that achieves state-of-the-art results on MLE-Bench among open-source systems by combining budget-aware MCTS planning, a Design-Decompose-Implement pipeline, and comparative reflective memory for cross-branch insight transfer.