LLM as Clinical Graph Structure Refiner: Enhancing Representation Learning in EEG Seizure Diagnosis

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Characterizing the Consistency of the Emergent Misalignment Persona

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agen...

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

GeoContra: From Fluent GIS Code to Verifiable Spatial Analysis with Geography-Grounded Repair

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Towards Improving Speaker Distance Estimation through Generative Impulse Response Augmentation

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Learning Multimodal Energy-Based Model with Multimodal Variational Auto-Encoder via MCMC Revision

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Born-Qualified: An Autonomous Framework for Deploying Advanced Energy and Electronic Materials

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Possibilistic Predictive Uncertainty for Deep Learning

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text

Fairness of Classifiers in the Presence of Constraints between Features

Subjects: “…ArXiv cs.AI Recent Papers…”
Get full text