ToolLLM is a general-purpose tool-use framework introduced by Qin et al. (2023)¹⁾ that enables open-source LLMs to effectively leverage a massive collection of real-world APIs. The paper has accumulated over 1,305 citations, establishing it as a foundational work in LLM tool-use research, building on earlier work like Toolformer²⁾) and Large Language Models as Tool Makers³⁾)). The framework addresses a critical gap between closed-source models (e.g., ChatGPT) and open-source alternatives by providing a comprehensive data construction, training, and evaluation pipeline.

arXiv:2307.16789

ToolBench is a large-scale instruction-tuning dataset containing 126,486 (instruction, solution path) pairs covering 16,464 real-world RESTful APIs spanning 49 categories from RapidAPI Hub⁴⁾. The dataset was automatically constructed using ChatGPT (gpt-3.5-turbo-16k) through a three-phase process:

• Single-tool instructions: Tasks solvable with a single API
• Intra-category multi-tool instructions: Tasks requiring multiple APIs from the same category
• Intra-collection multi-tool instructions: Tasks spanning APIs across different categories

DFSDT is a novel reasoning algorithm that expands the search space beyond linear chain-of-thought by evaluating multiple reasoning traces in a depth-first search manner.

The search process can be formalized as:

$$T^* = \arg\max_{T \in \mathcal{T}} R(T)$$

where $T$ is a reasoning trace in the search tree $\mathcal{T}$ and $R(T)$ is the reward (successful API execution). At each node, the LLM generates candidate actions, expands promising branches, and backtracks from failed paths.

ToolEval is an automatic evaluation framework using two metrics:

• Pass Rate: Percentage of instructions successfully executed within budget constraints
• Win Rate: Pairwise comparison of solution path quality, judged by ChatGPT

Both metrics show high correlation with human evaluation.

# Simplified ToolLLM inference loop with DFSDT
def dfsdt_search(instruction, api_retriever, llm, max_depth=5):
    apis = api_retriever.retrieve(instruction, top_k=5)
    root = Node(state=instruction, apis=apis)
    stack = [root]
    best_path = None
 
    while stack:
        node = stack.pop()
        if node.depth >= max_depth:
            continue
        # LLM generates candidate actions (API calls)
        actions = llm.generate_actions(node.state, node.apis)
        for action in actions:
            observation = execute_api_call(action)
            child = Node(
                state=update_state(node.state, action, observation),
                parent=node, depth=node.depth + 1
            )
            if is_task_complete(child.state):
                path = reconstruct_path(child)
                if best_path is None or score(path) > score(best_path):
                    best_path = path
            else:
                stack.append(child)
    return best_path

• ToolLLaMA matches ChatGPT and approaches GPT-4 performance on ToolBench⁵⁾
• Outperforms Text-Davinci-003 and Claude-2 on tool-use tasks
• Strong zero-shot generalization to unseen APIs, tools, and categories
• Neural API retriever effectively selects relevant APIs from 16K+ candidates

• LATM: Large Language Models as Tool Makers
• ChemCrow: LLM Agent with Chemistry Tools
• RAP: Reasoning via Planning