Saltar al contenido

julio 2026

1582 artículos
Wiola: el SLM que se salta todas las reglas y no se parece a nada de lo que conoces
IA

Wiola: el SLM que se salta todas las reglas y no se parece a nada de lo que conoces

arXiv:2607.01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon. Wiola introduces five independently novel components: (i) Spiral Rotary Positional Encoding (SRPE), which embeds token positions on a three-dimensional helical manifold combining absolute, relative, and hierarchical positional signals; (ii) Gat

03/07/2026
¿Y si los LLMs aprendieran a usar APIs como un becario con un manual?
IA

¿Y si los LLMs aprendieran a usar APIs como un becario con un manual?

arXiv:2607.01465v1 Announce Type: new Abstract: Large language models are trained to predict the next token, not to act inside a specific API. In niche enterprise SaaS workflows -- where success means hitting the right endpoint with the right nested arguments in the right order -- this objective mismatch shows up as silent failures: dropped required fields, hallucinated tools, or early stops after a single read. We ask whether Reinforcement Learning with Verifiable Rewards (RLVR), applied direc

03/07/2026