The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: within a year, large organizations went from zero to dozens of internally built MCP servers. That speed created a governance crisis. Each team implemented authentication ind...
LLM agents translate natural-language context, which may include attacker-controlled text, into privileged tool calls, so authorization must remain effective even when an agent is prompt-injected or adversarially steered. The Model Context Protocol (MCP) has become a widely adopted interface for this boundary, yet its...
This work presents Task-to-Model Optimization (T2MO), a data-driven methodology for optimizing model selection in production coding workflows, and describes the methodology, optimization objective, evaluation protocol, and governance loop in a form suitable for production deployment and future empirical study.
Srinivasan Manoharan, Junhua Zhao, Fang Tu et al.· 0 citations
This work presents SCOUT (Selective Context Optimization for Universal Tooling for Universal Tooling), which reframes tool exposure as a context-selection problem, injecting only tools relevant to the current step, and reduces MCP tool-token consumption by 99%, cutting per-query inference cost at enterprise scale.
Olympia Saha, Amy Wang, Srinivasan Manoharan· 0 citations
A performance recovery framework based on Self-Distillation Fine-Tuning (SDFT) that effectively restores model capabilities and offers new insights into the internal mechanisms of self-distillation is introduced.
