Author

Yirui Shi

h-index 0 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

This work introduces Agent Harness Distillation (AHD), a framework for studying the security risks arising from inference-time harness extraction in AMAS and proposes a deception-based defense that reduces harness extraction effectiveness while preserving the utility of the protected agent.

Yu Cui, Wuli Yang, Yirui Shi et al. · arXiv.org · 0 citations

#software testing Preprint Aug 2026

DSA: Evidence-Aware LLM-Agent Orchestration for Multi-Market Stock Research

DSA is presented, an evidence-aware orchestration framework for multi-market stock research with large language model (LLM) agents that establishes implementation conformance for the tested software contracts, not superior report quality, forecasting accuracy, or investment returns.

Lingfeng Zhu, Yirui Shi · 1 citation