SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.07324 · EMNLP · 2024

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent

Ming Yan, Fei Huang, Xiaojun Quan, Ji Zhang, Weizhou Shen, Hongzhan Chen, Chenliang Li, Hehong Chen

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.07324.json · badge: /api/ran/2401.07324.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
x-plug/multi-llm-agent marked official in Papers with Code
Papers with Code archive
4 ran · 2 no recorded run
FunctionStatusWhere it lives
SimpleChatIO Ran
ran on a synthesized input · constructed an object; no result was computed
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("bed576a0bbc5aca7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

collab_agent_parser Ran
ran; our contract draft was wrong, not the code
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("b0051984c25d68c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_stream Ran
ran; our contract draft was wrong, not the code
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("67d55c8e9077d9e7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepare_logits_processor Ran
ran; our contract draft was wrong, not the code
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("93c25411cf60d992")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ChatIO Not yet run
unverified (harvested, no recorded run)
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("3d81fd3240dba079")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

CollbaAgentV3 Not yet run
unverified (harvested, no recorded run)
x-plug/multi-llm-agent/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py
pointer only (licence: NONE) · get_code("52618fa24b988a40")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, x-plug/multi-llm-agent when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
prepare_logits_processor
brick of this paper's assembly: helper
4 other papers
3 dated earlier, 1 later
2305.14233 (2023-05)
Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
2310.16450 (2023-10)
CLEX: Continuous Length Extrapolation for Large Language Models
2312.02614 (2023-12)
Prompt Optimization via Adversarial In-Context Learning
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large Language Model (LLM) agents significantly extend the capabilities of standalone LLMs, empowering them to interact with external tools (e.g., APIs, functions) and complete various tasks in a self-directed fashion. The challenge of tool use demands that LLMs not only understand user queries and generate answers accurately but also excel in task planning, tool invocation, and result summarization. While traditional works focus on training a single LLM with all these capabilities, performance limitations become apparent, particularly with smaller models. To overcome these challenges, we propose a novel approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. Each component is implemented by a single LLM that focuses on a specific capability and collaborates with others to accomplish the task. This modular framework facilitates individual updates and the potential use of smaller LLMs for building each capability. To effectively train this framework, we introduce a two-stage training paradigm. First, we fine-tune a backbone LLM on the entire dataset without discriminating sub-tasks, providing the model with a comprehensive understanding of the task. Second, the fine-tuned LLM is used to instantiate the planner, caller, and summarizer respectively, which are continually fine-tuned on respective sub-tasks. Evaluation across various tool-use benchmarks illustrates that our proposed multi-LLM framework surpasses the traditional single-LLM approach, highlighting its efficacy and advantages in tool learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.07324")
get_code_for_paper("2401.07324")
have("2401.07324")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.07324.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.07324.svg)](https://syntology.ai/paper/2401.07324)

Connect an agent — have() is free.