Tag
tool use
Tool use refers to letting LLMs and agents call search, code execution, databases, or external APIs only when needed, instead of relying on generation alone. The hard part is deciding when a tool helps and when it just adds latency, cost, or failure modes, especially in multimodal agents and production workflows.
4 articles
New NLP papers map agent memory and tool use
A June 24 arXiv roundup highlights agent memory, tool-use signals, and conversational search papers that push practical NLP forward.
BenchLM ranks the best AI agent models for 2026
BenchLM’s 2026 rankings compare 49 models across agentic tasks like tool use, browsing, terminal work, and computer control.
AWS explains AI agents in one workflow
I break AWS’s AI agent explainer into a practical workflow and give you a copy-ready template for planning, tools, memory, and reflection.
Act Wisely: Teaching Agents When Not to Call Tools
A new training scheme, HDPO, aims to cut blind tool use in multimodal agents by separating accuracy from tool efficiency.