1
How to Train a Critic Stably and Efficiently
新規
score 0.92
cs.LGcs.AIcs.CL
2
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
新規
score 0.92
cs.CLcs.AIcs.SE
メモ
3
EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings
新規
score 0.92
cs.CVcs.AI
メモ
4
Prime Agent: A Self-Improving RLM Harness
新規
score 0.91
cs.AIcs.CLcs.SE
メモ
5
When "Do Not" Is Not Deny: Security Rules in CLAUDE.md vs Built-In Controls
新規
score 0.91
cs.HCcs.CR
メモ
6
Robustness of Anomaly Detection Models for Industrial Control Systems under Training-Time Data Contamination
新規
score 0.91
cs.CRcs.LG
メモ
7
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles
新規
score 0.91
cs.AI
メモ
8
The Interaction Tax: When Communication Erases Diversity in Multi-Agent Teams
新規
score 0.91
cs.MAcs.AI
メモ
9
Interpretable AI with Local Distillation
新規
score 0.91
stat.MEcs.LGstat.ML
メモ
10
Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition
新規
score 0.9
cs.CRcs.AI
メモ
11
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
新規
score 0.9
cs.AI
メモ
12
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
新規
score 0.88
cs.AIcs.CL
メモ
収集ソース
arXiv (AI) arXiv (Security)