Today’s frontier report
Research Pool → Jev → Edition
3qk7 · AI LOCAL LABS TECHNICAL SCOUTING

AI FRONTIER

Signals worth understanding before they become obvious.

2026-09-29
03
testresearchincremental

Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline

论文摘要:Auditing and Repairing LLM-as-Judge Failures in a Production Text-to-SQL Pipeline:围绕大语言模型的能力、评测或对齐问题展开,适合关注方法与实验结果。

논문이나 데모를 보는 단계를 넘어 실제 워크플로에서 시험해 볼 만한 수준에 가깝습니다.

arXiv cs.CL
04
watchagentsnew architecture

Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

论文摘要:A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load at runtime to extend its capabilities for a s...

당장 도입할 필요는 없지만 계속 추적할 가치가 있는 기술 신호입니다.

arXiv cs.AI