# NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models

arXiv: https://arxiv.org/abs/2609.35338 · HTML: https://mlsanity.com/paper/2609.35338/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 8 of its 59 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 8 of 8)

- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [Latent Geometry Beyond Search: Amortizing Planning in World Models](https://mlsanity.com/paper/2605.08732/) (2026)
- [Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models](https://mlsanity.com/paper/2605.07514/) (2026)
- [ACID: Action Consistency via Inverse Dynamics for Planning with World Models](https://mlsanity.com/paper/2607.02403/) (2026)
- [Structure is information: structural identifiability mappings for machine learning with partially observed dynamical systems](https://mlsanity.com/paper/2502.04131/) (2025)
- [Online Bayesian Experimental Design for Partially Observed Dynamical Systems](https://mlsanity.com/paper/2511.04403/) (2025)
- [Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework](https://mlsanity.com/paper/2602.18008/) (2026)
- [Reconstruction of glymphatic transport fields from subject-specific imaging data, with particular emphasis on cerebrospinal fluid flow and tracer conservation](https://mlsanity.com/paper/2605.00730/) (2026)

## Abstract (arXiv)

Mechanistic discovery in neuronal microenvironments requires interventions and measurements that separate competing explanations of solute transport and neuronal response. Predictive accuracy cannot settle the question: a real mechanistic change and an error in the computational twin leave the same signature in sparse observations. We formalize this twin confounding and reason over a joint mechanism--discrepancy belief, designing experiments that separate the two. NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism--Intervention--Observation--Outcome (MIOY) graph, whose supported relations compile into executable programs carrying discrepancy-adjusted acceptance bounds. We evaluate on simulated brain-fluid tracer-transport worlds adjudicated by an independently frozen finer-mesh reference solver, and on donor-disjoint public current-clamp recordings of cortical neurons. Counting only relations that reach a certified terminal status, and scoring abstentions as unresolved for every method, at a matched budget of 16 experiments over 32 source units NeuronDiscover resolves 4.0 relations per assigned world against 3.4 for the strongest baseline and 3.2 without graph revision, at 5% false support and 82% scope accuracy. Joint mechanism--discrepancy acquisition resolves 3.8 relations versus 2.9 for plug-in expected information gain; discrepancy-adjusted verification lowers accepted-program failure from 15% to 9% at 60% acceptance coverage; and transfer to the recordings yields 1.94 versus 1.53 relations per assigned world. Correctness is adjudicated within declared model worlds and archival recordings.