Callability Is Not Operability: Controlled Interface Interventions for LLM Agents
Source
arxiv.org
Author
Zihao Wang
Date
Why it matters
If you write MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → servers or AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → tools, this is a checklist for exposing the state an agent needs to recover: execution lifecycle, explicit external-effect semantics, machine-readable results, postcondition verification.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
articleMLLMs Fail to Refuse when Using Tools AgenticallyRikiya Takehi, Ryo Hachiuma, Shaona Ghosh, Dan Zhao, Yu-Chiang Frank Wang, Yusuke Hirota
articleThe Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent BehaviorXiangzhe Xu, Hamidreza Saghir, Qianhui Wu, Marc-Alexandre C\^ot\'e, Tong Wang, Kiran Lakkaraju, Kexin Pei, Xiangyu Zhang
articlePosition: Multi-Agent Systems Should Prioritize Concurrency ControlXin Yang, Letian Li, Zimo Ji, Terry Jingchen Zhang, Wenyuan Jiang