2 papers
cs.AI2026
AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents
Hailin Zhong, Shengxin Zhu
Foundation-model agents are often modeled as policies over an observed state. In deployed systems, however, a runtime may intervene only after the model has emitted a semantic prop…
cs.SE2026
AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
Hailin Zhong, Shengxin Zhu
Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanati…