AINeutralarXiv – CS AI · 18h ago6/10
🧠
Agentic Search for Counterfactual Recourse under Fixed LLM Budgets
Researchers propose Comp-MCTS, an AI framework that efficiently generates multiple counterfactual explanations under limited LLM budget constraints by using tree-search algorithms to allocate queries toward novel intervention directions. The approach demonstrates superior performance in producing diverse, validated counterfactuals compared to existing single-candidate and multi-candidate baselines on real-world datasets.