Live intelligence

Latest AI updates

2 updates
Research

CCW-Net Uses Interventional Mediation Analysis for Causal Concept Explanations

Researchers introduce Causal Concept Wrapper Network (CCW-Net), which uses interventional mediation analysis as a training objective to align concept-based explanations with model outputs. The method targets necessity, sufficiency, and independence of concept representations through counterfactual concept representations. Mediation analysis is also proposed as an evaluation tool to quantify how much model output is causally attributable to each concept label combination. The approach is evaluated in aircraft control, driving, and image classification settings.

concept-based interpretabilitycausal inferencemodel evaluation
Research

Framework Estimates Causal Value of Intervening in AI Agent Trajectories

Researchers introduce a methodologically grounded framework for evaluating the causal effects of randomized interventions, such as verification or screening, within AI agent trajectories. Using a relatively small dataset collected under randomized interventions, the approach estimates dynamic causal effects for contextual intervention policies and derives structural parameters for safety leaderboards. Applied to tau-bench Retail, ToolSandbox, and ImpossibleBench, the authors find intervention effects vary substantially across agent actions and states. The work positions causal inference as a research agenda for reliable agent deployment.

agentic AIcausal inferenceAI evaluation