arXiv Machine Learning September 24, 2026 By Mengran Li, Bo Li, Chengyang Zhang, Yang Yan, Jinfeng Xu, Zhenchao Tang

Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

3d ago

Interpretable-by-Design Descriptor Portfolios Match a 2048-Dimensional Foundation Embedding on Low-Data Molecular Assays

The study evaluates whether a portfolio of compact, semantically named descriptor blocks can match the performance of a 2048‑dimensional CheMeleon embedding in low‑data molecular assays. Using a fixed 11‑dimensional physicochemical base and greedily adding provenance‑screened blocks, the portfolio achieves a mean test AUC of 0.762 across nine ADME/Tox assays, comparable to CheMeleon’s 0.764 and better than Mordred’s 0.756. The results meet a predeclared pooled parity threshold but not all per‑assay thresholds, and further analysis confirms the competitiveness of the auditable representation while highlighting unresolved assay‑level differences.

By Yiqi Yao, Miquel Duran-Frigola

rag

arXiv AI

Aug 7

CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction

arXiv:2608. 05359v1 Announce Type: new Abstract: CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP.

By Jose A. Bird

llms agents benchmarks

arXiv AI

Jul 7

EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

arXiv:2512. 22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings.

By Chama Bensmail

safety

arXiv Machine Learning

Jul 21

GeneSpeak-FP: Target and Compound Retrieval from Observed Cell-Level Perturbation Signatures

arXiv:2607. 17671v1 Announce Type: new Abstract: Large-scale single-cell perturbation atlases make it possible to ask an inverse question: given an observed transcriptional response, which annotated targets and compounds in a fixed library are most consistent with that response?

By Kseniia Vaniushkina, Jeongmin Lim, Jinyong Park

llms rag safety

arXiv AI

2d ago

From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

The paper introduces PhenoAIR, a reliability‑aware multi‑agent framework for predicting mechanisms of action (MOA) from Cell Painting morphological profiles. It treats retrieved neighbors as uncertain evidence, calibrating their reliability based on source, phenotype stability, and mechanism confusion, and refines predictions through controller‑guided evidence evaluation. PhenoAIR is benchmarked on JUMP Cell Painting data and outperforms both representation‑matching and LLM‑based baselines across controlled, realistic, and open‑world settings.

By Jiayuan Chen, Botao Yu, Tianyu Liu, Thai-Hoang Pham, Meng Wu, Ping Zhang

llms agents benchmarks

arXiv Computation and Language

Sep 15

HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

arXiv:2609.15938v1 Announce Type: new Abstract: Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems com...

By Jieyuan Liu, Mengzhou Hu, Jefferson Chen, JungHo Kong, Pratibha Jagannatha, Yiming Gao, Dexter Pratt, Hsin-Yuan Lee, Zhiting Hu, Trey Ideker, Wei Wang, Eric P. Xing, Zhen Wang

llms agents

One email a morning, machine-written

Related stories

Interpretable-by-Design Descriptor Portfolios Match a 2048-Dimensional Foundation Embedding on Low-Data Molecular Assays

CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction

EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs

GeneSpeak-FP: Target and Compound Retrieval from Observed Cell-Level Perturbation Signatures

From Retrieval to Reasoning: Agentic Mechanism Prediction from Cell Painting Profiles

HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses