# ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers

arXiv: https://arxiv.org/abs/2510.19791 · HTML: https://mlsanity.com/paper/2510.19791/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 14 of its 68 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 14 of 14)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Efficient Natural Language Response Suggestion for Smart Reply](https://mlsanity.com/paper/1705.00652/) (2017)
- [The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey](https://mlsanity.com/paper/2404.11584/) (2024)
- [Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents](https://mlsanity.com/paper/2310.19923/) (2023)
- [BM25S: Orders of magnitude faster lexical search via eager sparse scoring](https://mlsanity.com/paper/2407.03618/) (2024)
- [Advancing Reasoning in Large Language Models: Promising Methods and Approaches](https://mlsanity.com/paper/2502.03671/) (2025)
- [Control Illusion: The Failure of Instruction Hierarchies in Large Language Models](https://mlsanity.com/paper/2502.15851/) (2025)
- [A Survey of Model Architectures in Information Retrieval](https://mlsanity.com/paper/2502.14822/) (2025)
- [A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?](https://mlsanity.com/paper/2411.01414/) (2024)
- [Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers](https://mlsanity.com/paper/2411.04403/) (2024)
- [LGAI-EMBEDDING-Preview Technical Report](https://mlsanity.com/paper/2506.07438/) (2025)
- [QZhou-Embedding Technical Report](https://mlsanity.com/paper/2508.21632/) (2025)

## Built on by (most cited first, 7 of 7)

- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning](https://mlsanity.com/paper/2601.07782/) (2026)
- [Risk-Aware Reranking for Agentic Tool Retrieval](https://mlsanity.com/paper/2608.22751/) (2026)
- [Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents](https://mlsanity.com/paper/2606.07538/) (2026)
- [FitText: Evolving Agent Tool Ecologies via Memetic Retrieval](https://mlsanity.com/paper/2605.02411/) (2026)
- [Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching](https://mlsanity.com/paper/2609.02035/) (2026)
- [From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation](https://mlsanity.com/paper/2610.20388/) (2026)

## Abstract (arXiv)

Tool calling has become increasingly popular for Large Language Models (LLMs). However, for large tool sets, the resulting tokens would exceed the LLM's context window limit, making it impossible to include every tool. Hence, an external retriever is used to provide LLMs with the most relevant tools for a query. Existing retrieval models rank tools based on the similarity between a user query and a tool description (TD). This leads to suboptimal retrieval as user requests are often poorly aligned with the language of TD. To remedy the issue, we propose ToolDreamer, a framework to condition retriever models to fetch tools based on hypothetical (synthetic) TD generated using an LLM, i.e., description of tools that the LLM feels will be potentially useful for the query. The framework enables a more natural alignment between queries and tools within the language space of TD's. We apply ToolDreamer on the ToolRet dataset and show that our method improves the performance of sparse and dense retrievers with and without training, thus showcasing its flexibility. Through our proposed framework, our aim is to offload a portion of the reasoning burden to the retriever so that the LLM may effectively handle a large collection of tools without inundating its context window.