tool-augmented-llm

This paper formalizes Persistent Semantic Entities (PSE) in tool-augmented LLM agents, showing that implicit state persists across sessions and can be exploited, with all tested models vulnerable to preference and instruction contamination.

ToolMenuBench is a benchmark for evaluating tool-menu filtering strategies in multi-step LLM agents. It shows that causal minimal tool filtering significantly improves task success and reduces token usage compared to unfiltered exposure.