Adding shared debugging memory, hyperparameter tuning enforcement, and Thompson-sampling backtracking to tree-search agents recovers wasted compute and improves MLE-bench scores with the same language model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Recovering Wasted Compute in Autoresearch Agents
Adding shared debugging memory, hyperparameter tuning enforcement, and Thompson-sampling backtracking to tree-search agents recovers wasted compute and improves MLE-bench scores with the same language model.