NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution

2026-07-04

AI Summary

This work addresses the challenge of insufficient interpretability and traceability in open-domain critical scenario attribution by proposing NeSy-CSA, a novel framework that introduces neuro-symbolic methods to this task for the first time. NeSy-CSA achieves structured and traceable attribution through a pipeline that selects relevant factors, constructs dependency-aware evidence graphs, and integrates symbolic reasoning with neural inference. Its core innovations include atomic symbolic operations, evidence-constrained neural reasoning, and a dual-level evaluation mechanism assessing both process and outcome. Evaluated across four decision-making environments, the framework outperforms large language model baselines by 18.32% and 13.67% on two interventional attribution effectiveness metrics, respectively.

Abstract

Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems. Reasoning about such criticality can be formulated as an attribution problem. However, across different decision-making tasks, the causes of criticality may involve diverse state variables, interaction patterns, and failure mechanisms, making attribution an inherently open-ended problem beyond predefined explanation spaces. Existing attribution methods still struggle to balance open-ended reasoning flexibility with the interpretability and traceability required for critical scenario reasoning. To address this limitation, we propose NeSy-CSA, a neuro-symbolic framework that transforms open-ended critical scenario attribution from unconstrained explanation generation into structured and traceable reasoning. NeSy-CSA narrows the attribution space by selecting relevant factors, makes the reasoning process traceable through a dependency-aware evidence graph, and executes symbolic reasoning procedures derived from atomic operations, coordinated with evidence-constrained neural inference to support flexible open-ended attribution. We further introduce a process-level and result-level assessment module to evaluate the structural validity of the attribution process and the behavioral effectiveness of the attribution results under controlled interventions. Experiments across four decision-making environments show that NeSy-CSA improves two intervention-based measures of attribution effectiveness by 18.32% and 13.67% over LLM-based baselines. These results demonstrate its potential to transform discovered critical scenarios into reusable knowledge for subsequent testing and safety analysis.

Problem

• critical scenario attribution
• open-ended reasoning
• neuro-symbolic
• interpretability
• traceability

Innovation

• Neuro-Symbolic Reasoning
• Critical Scenario Attribution
• Open-Ended Explanation
• Evidence Graph
• Interpretable AI