Actualités & Insights

Restez à la pointe de la tech

Veille technologique, conseils d'experts et actualités sur l'IA, la cybersécurité, les réseaux et la transformation digitale.

676
Articles publiés
12231
Lectures cumulées
0
Auteurs
Tous 676 🔐 Cybersécurité 417 🤖 Intelligence Artificielle 253 💻 Tech & Transformation Digitale 6
Chargement…
🧠
Intelligence Artificielle

trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories

arXiv:2609.00038v1 Announce Type: new Abstract: Outcome-only evaluation is the production default for LLM agents: show a judge the request and the final reply and ask whether it was handled well. The metric is structurally blind to an agent that reaches the right answer the wrong way. We measure that blind spot where ground truth is known by construction: a deterministic…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning

arXiv:2609.00014v1 Announce Type: new Abstract: Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid, synthetic personas that flatten individual variation, rely on stereotypes, and miss the nuanced signals driving actual human preferences. We introduce profile behavioral grounding,…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

Asymmetric Within-Document Predictive Learning for Scientific Document Representation

arXiv:2608.28625v1 Announce Type: new Abstract: We study predictive pretraining for scientific document representation using the discourse structure of papers. We propose SciJEPA, a citation-free framework that learns through asymmetric within-document prediction: title and abstract representations are used to predict method representations, and method representations are…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments

arXiv:2608.28624v1 Announce Type: new Abstract: Accurate interpretation of single-visit and longitudinal clinical assessments for Parkinson's disease is time-consuming and often depends on specialist expertise. Although large language models (LLMs) can generate natural language summaries, they frequently lack domain-specific clinical grounding and struggle to produce…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

Looking Again: Measuring Sycophancy in the Reasoning Chains of Multimodal Models Under Pressure

arXiv:2608.28623v1 Announce Type: new Abstract: Large multimodal reasoning models (LMRMs) are getting increasingly capable, primarily through generating explicit chain-of-thought reasoning before answering. In language models it has been observed that this performance often comes with sycophancy, the tendency of a model to agree with the user over the evidence. However, for…

--
Équipe
1 min
Lire l'article
🧠
Intelligence Artificielle

From GenAI Virtual Patient Dialogue Logs to Teacher-Interpretable Process Evidence: A Learning Analytics Study in Higher Education

arXiv:2608.28619v1 Announce Type: new Abstract: Medical history taking is a dialogue-based clinical reasoning task in which learners must gather, organise, and integrate patient information while the consultation unfolds. Generative AI-powered virtual patients (GenAI VPs) make repeated history taking practice scalable and preserve full turn by turn dialogue. However, these…

--
Équipe
1 min
Lire l'article