concept · created Jun 4, 2026 · updated Jun 4, 2026

tool-use

#tool-use#agent-engineering#llm-agent

Tool use — the third component of the agent anatomy: equipping the LLM to call external APIs for what its weights don’t contain — current information, code execution, proprietary data sources, actions in the world (Weng 2023). “Equipping LLMs with external tools can significantly extend the model capabilities.”

The load-bearing insight, from the MRKL arithmetic experiment: knowing when and how to call a tool is the hard part, and it’s bounded by the LLM’s capability — not by the tool. This is the seed of the modern ACI design discipline.

The lineage Weng surveys

SystemYearIdea
MRKL (Karpas et al.)2022”Modular Reasoning, Knowledge and Language” — a neuro-symbolic router; the LLM dispatches queries to expert modules (neural or symbolic: calculator, currency converter, weather API). Experiment: a 7B model failed to reliably extract arguments for basic arithmetic — verbal math is harder than explicit math.
TALM / Toolformer (Parisi et al. / Schick et al.)2022–23Fine-tune the LM to use APIs; expand the training set only when an API-call annotation actually improves the output (self-supervised tool learning).
ChatGPT Plugins / function calling (OpenAI)2023The productized form — tools provided by third parties (Plugins) or self-defined (function calls). The pattern this wiki’s 2026 sources take as baseline.
HuggingGPT (Shen et al.)2023ChatGPT as a controller orchestrating other models — see below.
API-Bank (Li et al.)2023A benchmark for tool-augmented LLMs — see below.

HuggingGPT — the LLM as controller

A four-stage loop where ChatGPT plans and routes work to HuggingFace models:

  1. Task planning — parse the user request into tasks, each with task type, id, dependencies, args (few-shot prompted). Dependencies let one task consume another’s output.
  2. Model selection — frame model choice as a multiple-choice question over a (filtered) candidate list; the LLM outputs a model id + reason in strict JSON.
  3. Task execution — expert models run and log results.
  4. Response generation — the LLM summarizes execution results for the user.

Weng flags three real-world frictions: efficiency (many LLM rounds + model calls), reliance on a long context window, and stability of LLM outputs + external services. This is an early, explicit instance of orchestrator-workers.

API-Bank — evaluating tool use at three levels

A benchmark: 53 tools, 264 dialogues, 568 API calls. Because there are many APIs, the agent first searches an API search engine, then reads docs to make the call (the pseudocode loops: summarize → search → if found, gen_api_call → execute → refine). Three difficulty levels:

  • Level 1 — call: given an API description, decide whether to call it, call it correctly, and respond to its return.
  • Level 2 — retrieve: search for candidate APIs and learn to use them from documentation.
  • Level 3 — plan: for unclear requests (book a trip, schedule a meeting), chain multiple calls. (Maps onto task-decomposition.)

API-Bank is one of the wiki’s earliest agent-evaluation references — decision-by-decision scoring of a tool-use trajectory.

The 2026 descendants

  • agent-computer-interface (ACI) — Weng’s “knowing when & how” turned into a design discipline: tools designed for the agent’s goals (not raw API endpoints), descriptions that say when to use them, structured errors. The modern answer to the MRKL argument-extraction failure.
  • model-context-protocol (MCP) — the standardized plug for external systems into agent harnesses; the productized successor to ad-hoc Plugins.
  • agent-evaluation — API-Bank’s level structure prefigures runtime tool-use evals.

Referenced by 7

2026-06-04-llm-powered-autonomous-agents agent-computer-interface agent-evaluation llm-agent task-decomposition lilian-weng openai
esc