Papers2

#multi-turn decision making

SkillOrchestra: Learning to Route Agents via Skill Transfer

Jiayu Wang, Yifei Ming et al.Feb 23arXiv

SkillOrchestra is a new way to make teams of AI models and tools work together by thinking in terms of skills, not just picking one big model for everything.

#agent orchestration#model routing#skill discovery

Not triaged yet

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Intermediate

Xiaoyu Tian, Haotian Wang et al.Jan 29arXiv

ASTRA is a fully automated way to train tool-using AI agents by making both their practice stories (trajectories) and their practice worlds (environments) without humans in the loop.

#tool-augmented agents#multi-turn decision making#verifiable environments

Not triaged yet