5 papers · 1 filter
EvoSteer: Online Self-Evolving Graph Orchestration via Reference-Anchored Credit Assignment
Mingda Zhang, Hanwen Zhang, Qiang Huang +5
In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However, existing self-evolving orche…
R Flow: Recursive Self-Improvement via Recursive Skill Evolution
Mingda Zhang, Qiang Huang, Yanjin Li +4
LLM-based agents can improve themselves across tasks by reusing and revising the skills they orchestrate into executable procedures. Flow-based training fits this loop: it samples…
Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs
Haoran Shou, Haoyue Liu, Yu Huo +2
Large language models can solve increasingly diverse reasoning tasks, yet their performance remains highly sensitive to task prompts, intermediate instructions, and the way reusabl…
SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration
Mingda Zhang, Tiesunlong Shen, Haoran Luo +4
In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods sti…
FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +5
In recent years, agentic workflows have been widely applied to solve complex human tasks. However, existing workflow construction still faces key challenges, including human-depend…