A-JIT: Agentic Just-In-Time Software Construction
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA
Support Discovery With Iteratively Reweighted Least Squares for Fixed-Charge Network Flow
City Editing: Hierarchical Agentic Execution for Dependency-Aware Urban Geospatial Modifi…
Decision-Focused Active Learning for Scale-Aware Critical-Materials Recovery
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reas…
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
Spec-Harness: Measuring and Improving Behavioral Adequacy of LLM-Synthesized Formal Speci…
PRAGMA: Evaluating Personalized Guidance with Memory Alignment in Lifelong Conversations
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossl…
Elsewise: Authoring Open-ended Interactive Narrative with Possibility Space Visualization
What Fixed-Rollout pass@k Evaluations Can Identify
Multi-Agent Agentic Graph Learning via Structural Signatures
Reliability-Aware Hybrid-K Ensemble Selection for Cervical Cytology Classification: Integ…
Distributed Physical Layer Authentication and Collaborative RSMA in Non-Terrestrial Netwo…
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representati…
XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
ContractEval: Query-Conditioned Execution Matching for Procedural Instruction Conformance
Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Ex…
The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents
Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph At…
The Biggest Risk of Embodied AI is Governance Lag
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in…
CityPlanner: A Sandbox Agent for Executable Urban Planning
MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks