3 papers
POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
Iñaki Dellibarda Varela, R. Sendra-Arranz, Pablo Romero-Sorozabal +5
Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characte…
Sensorimotor Self-Recognition in Multimodal Large Language Model-Driven Robots
Iñaki Dellibarda Varela, Pablo Romero-Sorozabal, Diego Torricelli +5
Self-recognition -- the ability to maintain an internal representation of one's own body within the environment -- underpins intelligent, autonomous behavior. As a foundational com…
Rethinking the Illusion of Thinking
Iñaki Dellibarda Varela, Pablo Romero-Sorozabal, Eduardo Rocon +1
Earlier this year, Apple ignited controversy by publishing "The Illusion of Thinking," prompting heated debate within the AI community. Critics seized upon the findings as conclusi…