Cycle-of-Science: Reliable Reasoning through Counterfactual Verification for Agent Decision Making

Large Language Models have significantly advanced autonomous agents through their sophisticated perception and execution capabilities. Despite effective, agents still struggle with robust decision-making due to passive learning from similar experiences that often confound correlation with causality. Inspired by the Scientific Method, we propose a Cycle-of-Science framework that autonomously explores potential causal pathways through an iterative loop of \textit{Hypothesis, Experiment, and Validation}, enabling agents to identify truly effective causal dependencies. To be specific, we first leverage causal knowledge to guide the initial hypotheses generation. These hypotheses are then analyzed through experiments using counterfactual samples. Afterward, we perform causal analysis to quantify effects of interventions, deriving well-validated hypotheses for next agent steps. To train our policy, we further introduce a two-stage pipeline that integrates supervised fine-tuning with Counterfactual Preference Optimization, which constructs preference signals from intervention outcomes to reinforce validated reasoning chains. Experiments on benchmarks demonstrate that our method achieves superior performance over state-of-the-art approaches.

Large Language Models have significantly advanced autonomous agents through their sophisticated perception and execution capabilities. Despite effective, agents still struggle with robust decision-making due to passive learning from similar experiences that often confound correlation with causality. Inspired by the Scientific Method, we propose a Cycle-of-Science framework that autonomously explores potential causal pathways through an iterative loop of \textit{Hypothesis, Experiment, and Validation}, enabling agents to identify truly effective causal dependencies. To be specific, we first leverage causal knowledge to guide the initial hypotheses generation. These hypotheses are then analyzed through experiments using counterfactual samples. Afterward, we perform causal analysis to quantify effects of interventions, deriving well-validated hypotheses for next agent steps. To train our policy, we further introduce a two-stage pipeline that integrates supervised fine-tuning with Counterfactual Preference Optimization, which constructs preference signals from intervention outcomes to reinforce validated reasoning chains. Experiments on benchmarks demonstrate that our method achieves superior performance over state-of-the-art approaches.