# Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model

arXiv: https://arxiv.org/abs/2310.05155 · HTML: https://mlsanity.com/paper/2310.05155/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 41 references that are in the map.
- First posted on arXiv 8 Oct 2023.

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://mlsanity.com/paper/2303.04671/) (2023)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)

## Built on by (most cited first, 29 of 29)

- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [A Review of Large Language Models and Autonomous Agents in Chemistry](https://mlsanity.com/paper/2407.01603/) (2024)
- [Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance](https://mlsanity.com/paper/2410.12361/) (2024)
- [Acting Less is Reasoning More! Teaching Model to Act Efficiently](https://mlsanity.com/paper/2504.14870/) (2025)
- [UserBench: An Interactive Gym Environment for User-Centric Agents](https://mlsanity.com/paper/2507.22034/) (2025)
- [Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents](https://mlsanity.com/paper/2402.09205/) (2024)
- [SMART: Self-Aware Agent for Tool Overuse Mitigation](https://mlsanity.com/paper/2502.11435/) (2025)
- [Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2503.01763/) (2025)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution](https://mlsanity.com/paper/2401.13996/) (2024)
- [ToolRM: Outcome Reward Models for Tool-Calling Large Language Models](https://mlsanity.com/paper/2509.11963/) (2025)
- [xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning](https://mlsanity.com/paper/2510.08439/) (2025)
- [Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation](https://mlsanity.com/paper/2501.12432/) (2025)
- [GTool: Graph Enhanced Tool Planning with Large Language Model](https://mlsanity.com/paper/2508.12725/) (2025)
- [SoAy: A Solution-based LLM API-using Methodology for Academic Information Seeking](https://mlsanity.com/paper/2405.15165/) (2024)
- [EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents](https://mlsanity.com/paper/2412.13549/) (2024)
- [A Study on Training and Developing Large Language Models for Behavior Tree Generation](https://mlsanity.com/paper/2401.08089/) (2024)
- [Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent](https://mlsanity.com/paper/2603.05578/) (2026)
- [Schema as Parameterized Tools for Universal Information Extraction](https://mlsanity.com/paper/2506.01276/) (2025)
- [MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation](https://mlsanity.com/paper/2510.18383/) (2025)
- [Multi-Field Tool Retrieval](https://mlsanity.com/paper/2602.05366/) (2026)
- [IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment](https://mlsanity.com/paper/2606.08016/) (2026)
- [Controlling Tool Use with Heading-Specific Activation Steering](https://mlsanity.com/paper/2607.05790/) (2026)
- [PEARL: Plan Exploration and Adaptive Reinforcement Learning for Multihop Tool Use](https://mlsanity.com/paper/2601.20439/) (2026)
- [DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance](https://mlsanity.com/paper/2606.05728/) (2026)
- [Tunable Tool-Call Rates in LLM Agents via Representation Steering](https://mlsanity.com/paper/2608.25198/) (2026)
- [GRAFT: Graph-Tokenized LLMs for Tool Planning](https://mlsanity.com/paper/2605.11706/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable progress in utilizing tools, but their closed-source nature and high inference costs pose limitations on their adaptability, necessitating a valid method that leverages smaller, open-sourced models. In this paper, we introduce Toolink, a comprehensive framework that performs task-solving by first creating a toolkit and then integrating the planning and calling of tools through a chain-of-solving (CoS) approach. We first validate the efficacy of Toolink in harnessing the model's creativity and CoS ability on ChatGPT. Subsequently, we curate CoS-GPT, a chain-of-solving dataset designed for tool-using, and finetune the LLaMA-7B model. It results in LLaMA-CoS, a powerful open-source model with advanced tool-planning and tool-calling capabilities. Evaluation of diverse tasks from BIG-bench demonstrates its CoS ability matches that of ChatGPT while its performance surpasses the chain-of-thought approach. Further studies highlight the generalization of LLaMA-CoS to unseen tasks and showcase its capability in using toolkits not explicitly tailored for the target task, affirming its robustness in real-world scenarios.