3 papers
cs.SE2026
ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems
Akshey Sigdel, Rista Baral
Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and ineffi…
cs.CR2026
Guardrails as Infrastructure: Policy-First Control for Tool-Orchestrated Workflows
Akshey Sigdel, Rista Baral
Tool-using automation systems, from scripts and CI bots to agentic assistants, fail in recurring patterns. Common failures include unsafe side effects, invalid arguments, uncontrol…
cs.SE2026
Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance
Akshey Sigdel, Rista Baral
Tool use has become central to modern LLM agents, yet interface design is rarely isolated as an experimental variable. This paper studies whether schema based tool contracts and st…