3 papers
cs.AI2026
JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion
Zhengkai Tu, Mingda Zhang, Zijia Wang +2
A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid statute matching and ungrounde…
cs.MA2026
CollabFlow: Recursive Self-Improvement of Agent Collaboration
Xiao Huang, Mingda Zhang, Junming Zhang +5
Recursive self-improvement (RSI) lets a system improve from its own outcomes; in LLM-based multi-agent systems, Agents refine one another within a task, and outcomes improve how th…
cs.AI2026
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…