6 papers
Risk Architecture for AI-Native Engineering Teams: An Organizational Framework for Agentic System Governance
Laxmipriya Ganesh Iyer
Engineering management research has produced mature frameworks for software risk: ownership by feature, escalation by severity, and assurance by test coverage. These frameworks imp…
The Gate Is Only as Honest as Its Contracts: ContractGuard for the Contract Layer of Risk-Aware Causal Gating
Laxmipriya Ganesh Iyer, Rahul Suresh Babu
Risk-Aware Causal Gating (RACG) defends tool-augmented LLM agents against indirect prompt injection by removing dangerous tools from the agent's visible action space, so that even…
ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents
Rahul Suresh Babu, Laxmipriya Ganesh Iyer
Tool-augmented large language model agents increasingly operate over large tool libraries, but existing evaluations often focus on whether a model can call a tool correctly rather…
Capability Minimization as a Safety Primitive: Risk-Aware Causal Gating for Least-Privilege LLM Agents
Laxmipriya Ganesh Iyer, Rahul Suresh Babu
Modern decision systems increasingly rely on learned components whose outputs may be confident yet wrong, exposing downstream actions to costly errors. We introduce Risk-Aware Caus…
Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents
Rahul Suresh Babu, Laxmipriya Ganesh Iyer
Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or w…
ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
Rahul Suresh Babu, Laxmipriya Ganesh Iyer
Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and…