3 papers
cs.AI2026
ARCO: Adaptive Rubrics with Co-Evolution for Multi-Step LLM-Based Agents
Zihang Tian, Jingsen Zhang, Rui Li +3
Reinforcement learning for multi-step LLM agents often relies on scalar rewards that indicate success but cannot explain why a trajectory is good or bad. Rubric-based rewards impro…
cs.AI2026
Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective
Rui Li, Zeyu Zhang, Xiaohe Bo +4
Multi-agent architectures built on large language models (LLMs) have demonstrated the potential to realize swarm intelligence through well-crafted collaboration. However, the subst…
cs.CL2026
HAPS: Hierarchical LLM Routing with Joint Architecture and Parameter Search
Zihang Tian, Rui Li, Jingsen Zhang +3
Large language model (LLM) routing aims to exploit the specialized strengths of different LLMs for diverse tasks. However, existing approaches typically focus on selecting LLM arch…