collaborators

8 papers

cs.AI2026

Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces

Nicolás Astorga, Nabeel Seedat, Mihaela van der Schaar

Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making. Many real-world tasks require findin…

cs.LG2026

Skill Neologisms: Towards Skill-based Continual Learning

Antonin Berthon, Nicolas Astorga, Mihaela van der Schaar

Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable ma…

cs.AI2026

Learning Reasoning Rewards from Expert Demonstrations with Inverse Reinforcement Learning

Claudio Fanconi, Nicolás Astorga, Mihaela van der Schaar

Teaching large language models (LLMs) to reason during post-training typically relies on reinforcement learning with explicit outcome- or process-based reward functions. However, i…

cs.AI2026

CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators

Nicolás Astorga, Anita Kriz, Mihaela van der Schaar

Despite surpassing human performance across mathematics, coding, and other knowledge-intensive tasks, large language models (LLMs) continue to struggle with causal reasoning. A cor…

cs.AI2025

Timely Clinical Diagnosis through Active Test Selection

Silas Ruhrberg Estévez, Nicolás Astorga, Mihaela van der Schaar

There is growing interest in using machine learning (ML) to support clinical diagnosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequenti…

cs.CL2025

Continuously Updating Digital Twins using Large Language Models

Harry Amad, Nicolás Astorga, Mihaela van der Schaar

Digital twins are models of real-world systems that can simulate their dynamics in response to potential actions. In complex settings, the state and action variables, and available…