1 minute read

1 minute read

[Agent] Extending FunctionGemma: 270M 모델로 온디바이스 모바일 function calling 넓히기

6 minute read

[Agent] Extending FunctionGemma for Practical On-Device Mobile Function Calling

[Agent] Evolving Procedural Memory from User Traffic for Agentic Graphic Design: weight update 없이 skill bank를 키워 그래픽 디자인 에이전트를 진화

8 minute read

[Agent] Evolving Procedural Memory from User Traffic for Agentic Graphic Design

[Agent] MENTOR: Teacher-Optimized Reward로 Tool-Use를 SLM에 distill하는 on-policy RL

5 minute read

[Agent] MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation