9 papers
ROrch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop
Mingda Zhang, Yun Huang, Qiang Huang +7
In recent years, agentic orchestration has been widely applied to solve complex human tasks. However, existing orchestration learning still faces key challenges, including hand-des…
ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences
Mingda Zhang, Wenjin Liu, Tiesunlong Shen +6
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not exa…
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…
TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting
Wenjin Liu, Shen Pang, Chenxi Wang +6
Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and tem…
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…
Affective Flow Language Model for Emotional Support Conversation
Chenghui Zou, Ning Wang, Tiesunlong Shen +5
Large language models (LLMs) have advanced emotional support conversation, but existing alignment methods rely mainly on sparse preferences at the response level or outcomes at the…
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…
LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models
Tiesunlong Shen, Rui Mao, Jin Wang +4
Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignmen…
Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning
Wenjin Liu, Haoran Luo, Xueyuan Lin +5
Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accura…