In the news
The Bitter Lesson of Tool Calling
arXiv cs.AI · Published · 3 min read
In 30 seconds
- What happened
- Researchers compared programmatic tool calling via Python code against JSON-based tool calling across 14 language models on the BFCL v4 benchmark.
- Why it matters
- Matters for engineers building LLM agents who need to choose between code-based and JSON-based tool invocation approaches for production systems.
- Watch out
- Results are specific to BFCL v4 benchmark; real-world performance may vary depending on task complexity, tool diversity, and specific model versions deployed.
- agent
- llm
- language model
- tool use
- tool calling
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.