cs.ROOct 30, 2026

From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models

Authors: Gihyuk Ko

Organizations: NC AI

Abstract

Post-incident analysis of a robot foundation model poses a singular causal question: which internal components caused this failure, and to what degree? Mechanistic interpretability (MI), however, establishes general causal claims by decoding the concepts a policy has learned, yet knowing which concepts are encoded is insufficient for identifying the actual cause of a specific incident. In this position paper, we analyze this concept-malfunction gap by posing fault isolation in the framework of actual causality. Specifically, we formalize a fault-isolation query as a tuple of intervened internal components, counterfactual values, contingencies, and read-outs, and lay out conditions for it to be well-specified. Through this lens, we identify shortcomings of current MI approaches: they assume fixed contingencies and read out only immediate effects, letting backups obscure actual causes. We demonstrate on a toy example that these shortcomings can lead to conflicting verdicts. Lastly, based on the well-specification conditions, we outline four open research tasks toward closing the gap.

Figures & tables

Explore similar work

CardsList
  1. Detecting and Explaining Robot Policy Failures from Sparse Internal Features

    Nov 7, 2026Riad Ahmed, Sujosh Nag, Moniruzzaman Akash +1Robot Failure DetectionMechanistic Interpretability

  2. Interventional Causal Circuits for Safe Robot Action Testing and Failure Recovery

    Jul 16, 2026Naren Vasantakumaar, Tom Schierenbeck, Michael BeetzRobot Failure DetectionRobot Failure Recovery

  3. Actual causality in fault trees

    Jul 2, 2026Georgiana Caltais, Milan Lopuhaä-Zwakenberg, Mariëlle StoelingaActual CausalityCausal Attribution