Agents
Generative Interpretability via Scalable Neuro-Symbolic Models
arXiv:2609.13529v1 Announce Type: cross Abstract: As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality,
arXiv:2609.13529v1 Announce Type: cross Abstract: As the use of Large Language Models moves from chatbots into agentic systems, where outputs become actions with irreversible consequences on reality, the existing paradigm on AI Interpretability research, post-hoc interpretability, is structurally inadequate for safe and trustworthy model deployment: it explains behavior after the fact but cannot audit or intervene in an inference computation before it commits to an output. We therefore argue for a shift toward generative interpretability, an architectural property under which a model's inference pass natively exposes semantically meaningful checkpoints that are human-understandable and amenable to causal intervention. We show the merits of generative interpretability as comparison to other interpretability research paradigms, and propose Neuro-Symbolic Models as a concrete instantiation.
Related
- Contextual Invertible World Models: A Neuro-Symbolic Agentic Framework for Colorectal Cancer Drug Response
- MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems
Source: arXiv cs.AI | 2026-09-15