Saltar al contenido

julio 2026

1582 artículos
OriginBlame: el sistema que resuelve el caos de borrar datos de entrenamiento de IA
IA

OriginBlame: el sistema que resuelve el caos de borrar datos de entrenamiento de IA

arXiv:2607.13037v1 Announce Type: new Abstract: When a data contributor requests removal, model trainers face a practical gap: unlearning algorithms require a forget set, yet no tool can locate which training records belong to a given author. Existing provenance systems operate at file or dataset level, forcing catastrophic over-deletion. We present ob, a record- and token-level data provenance system that propagates author identity through data processing pipelines and resolves revocation requ

16/07/2026
El problema no es que los robots piensen, es que no tienen médula espinal
Tecnología

El problema no es que los robots piensen, es que no tienen médula espinal

arXiv:2607.13049v1 Announce Type: new Abstract: Foundation models have given robots a sophisticated brain for complex decision-making, yet deploying that intelligence into a physical platform still demands tedious, expert-driven calibration. This deployment gap, the robot's spinal cord, remains a primary bottleneck to scalable Embodied AI. Hence, we propose SPINE (Scalable Physical Integration with ageNtic Expertise): an agentic framework for systematically debugging and deploying bimanual robo

16/07/2026
Los LLM mienten en su razonamiento: un test deja al descubierto sus trucos de magia
IA

Los LLM mienten en su razonamiento: un test deja al descubierto sus trucos de magia

arXiv:2607.13069v1 Announce Type: new Abstract: Large language models produce chain-of-thought (CoT) reasoning that appears logically sound yet may not genuinely depend on its stated premises. We introduce interventional grounding audits, a black-box, step-level test of premise dependency: we intervene on a single premise by substituting its target predicate with a fresh symbol, re-run the model, and check whether each reasoning step's normalized conclusion (canonical predicate form) changes. W

16/07/2026
Cuando los robots aprenden a dudar: la nueva vuelta de tuerca de la IA neuro-simbólica con probabilidades
IA

Cuando los robots aprenden a dudar: la nueva vuelta de tuerca de la IA neuro-simbólica con probabilidades

arXiv:2607.13073v1 Announce Type: new Abstract: Neuro-symbolic AI based on $IFOL_B$ is a way to combine neural learning and symbolic reasoning to overcome limitations of purely neural systems (like lack of interpretability and logical structure) with formal logical machinery for self-reference. In this paper we expand the cognitive power of $IFOL_B$ by using the probability computation for the currently unknown sentences, based on Nilsson's probability structure for the $IFOL_B$. We introduce t

16/07/2026
Máquinas que aprenden solas: el futuro de los agentes autónomos ya no es ciencia ficción
Tecnología

Máquinas que aprenden solas: el futuro de los agentes autónomos ya no es ciencia ficción

arXiv:2607.13104v1 Announce Type: new Abstract: Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input. This survey frames modern self-improving agents as adaptive systems that convert experience into accumulated capability gains. We offer a system-level framework that represents a modern agent as a configuration coupling a foundation model with an op

16/07/2026
Por qué los modelos de lenguaje pequeños no entienden las moléculas (y cómo unas redes especializadas pueden salvarlos)
Tecnología

Por qué los modelos de lenguaje pequeños no entienden las moléculas (y cómo unas redes especializadas pueden salvarlos)

arXiv:2607.13115v1 Announce Type: new Abstract: Small language models (SLMs) have shown promise for zero-shot molecular property prediction from SMILES strings, yet they often suffer from structural blindness because sequence representations under-specify key graph-topological cues. We propose a modular Context-Augmented Prompting framework that enables agentic tool use at inference time: a trained GNN expert model provides a predictive hint with confidence, and a GNN extracts an instance-speci

16/07/2026
Cuando la IA necesita memoria de elefante: Oracle se lanza a resolver el gran problema de los agentes autónomos
IA

Cuando la IA necesita memoria de elefante: Oracle se lanza a resolver el gran problema de los agentes autónomos

arXiv:2607.13157v1 Announce Type: new Abstract: Agent memory is a systems problem for long-horizon agents. Practical deployments require retention of task state across extended conversations, recovery of user-specific facts and preferences across sessions, and accumulation of procedural knowledge from prior outcomes. These requirements extend beyond document retrieval: a memory layer must determine which interactions become durable state, how that state is scoped, how it is retrieved under late

16/07/2026
Cuando los humanos tienen que enseñar a las máquinas a no ser unos kamikazes: llega DROPJ
IA

Cuando los humanos tienen que enseñar a las máquinas a no ser unos kamikazes: llega DROPJ

arXiv:2607.13172v1 Announce Type: new Abstract: We address the problem of safely training an agent policy and deploying a good and safe policy, in settings where the environment dynamics are unknown and no suitable reward function is available. In the context of safety-critical environments, we consider traditional reinforcement learning impractical and resort to the resource of human input. We introduce DROPJ, a human-centred method for both safe training and deployment. We first learn a world

16/07/2026