- Yapay Zeka · arxiv/cs.AI · 8 dk
Safe Bilevel Delegation: Runtime Safety Control for Multi-Agent LLM Systems
A formal framework that dynamically adjusts safety-efficiency trade-offs when delegating tasks to specialized AI sub-agents during execution.
2 Mayıs 2026 Oku → → - Yapay Zeka · arxiv/cs.AI · 5 dk
Self-Evolving Skills Let Language Models Learn From Long Context
Ctx2Skill uses multi-agent loops to automatically extract and refine skills from dense context without human annotation or external feedback.
1 Mayıs 2026 Oku → → - Yapay Zeka · arxiv/cs.AI · 3 dk
Multi-agent framework automates recommendation system tuning
AgenticRecTune uses specialized LLM agents to optimize configuration across pre-ranking, ranking, and re-ranking pipelines without manual tuning.
1 Mayıs 2026 Oku → → - Yapay Zeka · arxiv/cs.LG · 8 dk
Agentic AI Security Requires Layered Defense, Not Just Prompt Guards
A new framework maps AI agent vulnerabilities across seven architectural layers and four time horizons, revealing that 93% of research ignores the slowest, most dangerous threats.
28 Nisan 2026 Oku → →