Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
A-JIT: Agentic Just-In-Time Software Construction
arXiv cs.AI Security & Safety
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
arXiv cs.AI Research & Papers
Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA
arXiv cs.AI Research & Papers
Support Discovery With Iteratively Reweighted Least Squares for Fixed-Charge Network Flow
arXiv cs.AI Research & Papers
City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modifi…
arXiv cs.AI Research & Papers
Decision-Focused Active Learning for Scale-Aware Critical-Materials Recovery
arXiv cs.AI Research & Papers
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
arXiv cs.AI Research & Papers
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
arXiv cs.AI Research & Papers
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reas…
arXiv cs.AI Research & Papers
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
arXiv cs.AI Security & Safety
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
arXiv cs.AI Research & Papers
Spec-Harness: Measuring and Improving Behavioral Adequacy of LLM-Synthesized Formal Speci…
arXiv cs.AI Research & Papers
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
arXiv cs.AI Research & Papers
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossl…
arXiv cs.AI Research & Papers
Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization
arXiv cs.AI Research & Papers
What Fixed-Rollout pass@k Evaluations Can Identify
arXiv cs.AI Research & Papers
Multi-Agent Agentic Graph Learning via Structural Signatures
arXiv cs.AI Research & Papers
Reliability-Aware Hybrid-K Ensemble Selection for Cervical Cytology Classification: Integ…
arXiv cs.AI Research & Papers
Distributed Physical Layer Authentication and Collaborative RSMA in Non-Terrestrial Netwo…
arXiv cs.AI Research & Papers
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representati…
arXiv cs.AI Research & Papers
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
arXiv cs.AI Research & Papers
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance
arXiv cs.AI Research & Papers
Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Ex…
arXiv cs.AI Research & Papers
The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents
arXiv cs.AI Research & Papers
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph At…
arXiv cs.AI Policy & Regulation
The Biggest Risk of Embodied AI is Governance Lag
arXiv cs.AI Research & Papers
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in…
arXiv cs.AI Research & Papers
CityPlanner: A Sandbox Agent for Executable Urban Planning
arXiv cs.AI Research & Papers
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes
arXiv cs.AI Research & Papers
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks