4 papers
Testing the Planning Claims of LLM-Based Agents against Formal Semantics
Oriol Miro-Lopez-Feliu, Oscar Miró López-Feliu, Victor Gimenez-Abalos +3
LLM-based agents are increasingly credited with the competences of practical reasoning: planning, monitoring, and correcting their own actions. Their success is attributed to the p…
Correcting Within-Group Self-Selection Bias in Prioritized Replay
Oscar Miró López-Feliu, Herke van Hoof
Prioritized experience replay (PER) improves sample efficiency by replaying high-priority transitions, usually according to absolute temporal-difference error. In stochastic enviro…
From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models
Oscar Miró López-Feliu, Maya Ozbayoglu
A direction in activation space that changes safety-relevant behavior when steered is not necessarily one the model uses to produce that behavior on its own. We therefore ask wheth…
Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair
Oscar Miró López-Feliu, Daimy van Loo, Xanthos Kekkos +2
Fayyazi et al. (2025) recently proposed FACTER, a model-agnostic framework designed to jointly enforce fairness and statistical coverage in LLM-based recommendation through conform…