Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?

Researchers introduced AgenticInterpBench, a benchmark for circuit explanation in mechanistic interpretability, and HyVE, an agentic explainer that uses language models to analyze transformer circuit components. Testing across four LM backbones showed that HyVE recovers useful explanations, but reliable validation remains a key obstacle, with failures often arising from incomplete validation plans or code errors.

arXiv:2606.24026v1 Announce Type: new Abstract: Mechanistic interpretability has made substantial progress in automatically localizing circuits, but explaining what localized components do remains labor-intensive and difficult to standardize. In this work, we study whether language model LM agents can assist with this explanation problem once a circuit has already been identified. We introduce AgenticInterpBench, a benchmark for circuit explanation built from 84 semi-synthetic transformer circuits with 163 component-level annotations. We propose HyVE Hypothesize, Validate, Explain , an agentic explainer that analyzes each component through an iterative loop of observation, hypothesis generation, and causal validation, eventually producing a component-level explanation and a circuit-level task description. Across four LM backbones, HyVE recovers useful component- and task-level explanations, but no backbone is uniformly best. Our analysis shows that strong backbones usually form observation-grounded hypotheses, while failures more often arise later in the validation loop, through incomplete validation plans, code execution errors, or unresolved hypotheses. A case study on an arithmetic circuit in Llama-3-8B shows that the same formulation can extend beyond semi-synthetic benchmarks to naturally trained models. Overall, LM agents are promising circuit explainers, but reliable validation remains the key obstacle.