2 papers
cs.AI2026
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…
cs.MA2026
CEO Arena: Evaluating Long-Horizon Multi-Agent Decision-Making in Competitive Markets
An Yan, Yu Huo, Zhiwei Shang +2
Long-horizon competition tests agents' ability to coordinate business decisions under uncertainty and adapt to changing rival strategies. We introduce CEO Arena, a benchmark that u…