arXiv:2511.15534v1 Announce Type: new Abstract: There is growing interest in using AI agents for scientific research, yet fundamental questions remain about their capabilities as scientists and reviewers. To explore these questions, we organized Agents4Science, the first conference in which AI agents serve as both primary authors and reviewers, with humans as co-authors and co-reviewers. Here, we discuss the key learnings from the conference and their implications for human-AI collaboration in science.

arXiv:2509.26433v2 Announce Type: replace-cross Abstract: When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable, and auditable, a requirement increasingly expected by regulations. Decision trees such as CART provide clear and verifiable rules, but they are restricted to structured tabular data and cannot operate directly on unstructured inputs such as text. In practice, large language models (LLMs) are widely used for such data, yet prompting strategies such as chain-of-thought or prompt optimization still rely on free-form reasoning, limiting their ability to ensure trustworthy behaviors. We present the Agentic Classification Tree (ACT), which extends decision-tree methodology to unstructured inputs by formulating each split as a natural-language question, refined through impurity-based evaluation and LLM feedback via TextGrad. Experiments on text benchmarks show that ACT matches or surpasses prompting-based baselines while producing transparent and interpretable decision paths.

Background: Chatbots based on large language models (LLMs) have shown promise in evaluating the consistency of research. Previously, researchers used LLM to assess if randomized controlled trial (RCT) abstracts adhered to the CONSORT-Abstract guidelines. However, the consistency of artificial intelligence (AI) interventional RCTs align with the CONSORT-AI standards by LLMs remains unclear. Objective: The aim of this study is to identify the consistency of randomized controlled trials on AI interventions with CONSORT-AI using chatbots based on LLMs. Methods: This cross-sectional study employed six LLM models to assess the consistency of RCTs on AI interventions. The sample selection is based on articles published in JAMA Network Open, which included a total of 41 RCTs. All queries were submitted to LLMs through an API interface with a temperature setting of 0 to ensure deterministic responses. One researcher posed the questions to each model, while another independently verified the responses for validity before recording the results. The Overall Consistency Score (OCS), recall, inter-rater reliability and consistency of contents were analyzed. Results: We found gpt-4-0125-preview has the best average OCS (86.5%, 95%CI: 82.5%-90.5% and 81.6%, 95% CI: 77.6%-85.6%), followed by gpt-4-1106-preview(80.3%, 95%CI: 76.3%-84.3% and 78.0%, 95% CI: 74.0%-82.0%). The model with the worst average OCS is gpt-3.5-turbo-0125 (61.9%, 95%CI: 57.9%-65.9% and 63.0%, 95% CI: 59.0%-67.0%). Among the 11 unique items of CONSORT-AI, Item 2 (“State the inclusion and exclusion criteria at the level of the input data”) received the poorest overall evaluation across six models, with an average OCS of 48.8%. For other items, those with an average OCS greater than 80% across the six models included Items 1, 5, 8, and 9. Conclusions: GPT-4 variants demonstrate strong performance in assessing the consistency of RCTs with CONSORT-AI. Nonetheless, refining the prompts could enhance the precision and consistency of the outcomes. While AI tools like GPT-4 variants are valuable, they are not yet fully autonomous in addressing complex and nuanced tasks such as adherence to CONSORT-AI standards. Therefore, integrating AI with higher levels of human supervision and expertise will be crucial to ensuring more reliable and efficient evaluations, ultimately advancing the quality of medical research.

Nature Biotechnology, Published online: 19 August 2025; doi:10.1038/s41587-025-02770-1

A vast landscape of ‘undruggable’ cancer targets remains beyond the reach of conventional therapeutic agents. Recent advances in artificial intelligence (AI), however, are challenging this paradigm. Synthesizing insights from a Cancer Moonshot workshop, we argue that systemically addressing the undruggable target space with AI requires a new conceptual framework. We highlight the failure of current target taxonomies and the need for benchmarking datasets, and re-evaluate clinical validation for novel AI-driven modalities.