5 papers · 1 filter
IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems
Jie Mao, Pingchen Lu, Zikun Qu +6
Improving every agent in an LLM-based multi-agent system can be prohibitively costly, making it important to identify which agent should be prioritized to achieve the greatest syst…
AuthGateBench: Benchmarking LLMs as Authorization Gate
Zhixiong Zhuang, Jin Jia, Zhiwei Shang +1
Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large lang…
MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution
Zhiwei Shang, Yu Huo, Mingrong Gong +6
An agent harness is the code that organizes context, maintains state, and coordinates tool calls for a language model. We study how to improve the harness under a limited evaluatio…
Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs
Zhiwei Shang, Jiahang Sun, Mingrong Gong +9
Automated agentic workflow optimization relies on costly evaluations, making it essential to allocate a limited evaluation budget effectively. Multi-parent fusion can reuse designs…
Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
Mingze Kong, Zikun Qu, Zhongquan Zhou +7
The rapid evolution of agentic workflows has demonstrated strong performance of LLM-based agents in addressing complex reasoning tasks. However, existing workflow optimization meth…