Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Str…
arXiv cs.AI Research & Papers
A Query Engine for the Agents
arXiv cs.AI Research & Papers
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish…
arXiv cs.AI Research & Papers
Measuring Form and Function in Language Models
arXiv cs.AI Research & Papers
The Attentional White Bear Effect in Transformer Language Models
arXiv cs.AI Research & Papers
A Fresh Look at Lamarckian Evolution and the Baldwin Effect
arXiv cs.AI Research & Papers
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems
arXiv cs.AI Research & Papers
BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep N…
arXiv cs.AI Research & Papers
IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO D…
arXiv cs.AI Research & Papers
Architecture-driven Shift: towards a lightweight selector for capturing the trends of log…
arXiv cs.AI Research & Papers
Do Models Know Why They Changed Their Mind? Interpretability and Faithfulness of Chain-of…
arXiv cs.AI Research & Papers
Sense Representations Are Inducible Interfaces
arXiv cs.AI Research & Papers
Identifying and Understanding Human Values in Text: A Tailorable LLM-based Architecture
arXiv cs.AI Research & Papers
Behavioural Analysis of Alignment Faking
arXiv cs.AI Research & Papers
Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
arXiv cs.AI Research & Papers
RULER: Representation-Level Verification of Machine Unlearning
arXiv cs.AI Research & Papers
Cyberbullying Governance on Social Media: A Unified Framework from Content Identification…
arXiv cs.AI Research & Papers
A Policy-Driven Runtime Layer for Agentic LLM Serving
arXiv cs.AI Research & Papers
Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems
arXiv cs.AI Research & Papers
Rethinking Memory as Continuously Evolving Connectivity
arXiv cs.AI Research & Papers
Revealing Algorithmic Deductive Circuits for Logical Reasoning
arXiv cs.AI Research & Papers
When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models
arXiv cs.AI Research & Papers
Skill-Conditioned Gated Self-Distillation for LLM Reasoning
arXiv cs.AI Research & Papers
AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
arXiv cs.AI Research & Papers
PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Manageme…
arXiv cs.AI Research & Papers
SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit As…
arXiv cs.AI Research & Papers
Show, Don't TELL: Explainable AI-Generated Text Detection
arXiv cs.AI Research & Papers
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
arXiv cs.AI Research & Papers
Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential …
arXiv cs.AI Research & Papers
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations