The Flow has not summarised this story yet — read it at arXiv Machine Learning.
NeuronSifter is a decision‑centric Agent‑in‑Twin framework that uses an evolving biological digital twin instead of a fixed predictive model to prioritize central nervous system interventions. It compiles interventions into state‑conditional target‑occupancy representations, propagates them through a mechanism‑grounded World Action Model, and selects informative measurements to reduce decision uncertainty. The system is evaluated on Alzheimer’s disease scenarios, demonstrating adaptive evidence acquisition, uncertainty‑aware planning, and robustness to model discrepancy, while continuously refining its decision‑relevant representations with externally verified evidence.
The paper introduces Synthetic Universes, a benchmark that pairs well-known theoretical worlds with closely related twisted variants governed by noncanonical mechanisms. It evaluates scientific agents on each law twice: by testing predictive performance on unseen data and by checking if the law recovers the underlying generating mechanism. Results from a 60‑cell study show a dissociation between predictive adequacy and mechanism recovery, indicating that these are distinct scientific claims requiring separate tests.
DNative‑Twin is a graph‑native digital twin that records an AI agent’s committed decision as a typed trajectory, linking observed state, decision path, and authority. It re‑executes the decision mechanism under declared conditions, synchronizing and replaying the process in isolation to compare outcomes under controlled changes. Experiments on enterprise decision logs show that adding replay‑contract state and verification evidence improves unresolved‑divergence recall from 0 to 1.0, while end‑to‑end processing time rises from 0.794 to 8.889 seconds across 500–5,000 cases.
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
arXiv:2605. 09366v3 Announce Type: replace Abstract: Transforming neuroimaging data into clinically actionable biomarkers is a knowledge-intensive and labor-intensive process.
The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.