# Budget-Constrained Tool Learning with Planning

arXiv: https://arxiv.org/abs/2402.15960 · HTML: https://mlsanity.com/paper/2402.15960/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 25 Feb 2024.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis](https://mlsanity.com/paper/2307.12856/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head](https://mlsanity.com/paper/2304.12995/) (2023)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [An LLM Compiler for Parallel Function Calling](https://mlsanity.com/paper/2312.04511/) (2023)
- [GeneGPT: Augmenting Large Language Models with Domain Tools for Improved Access to Biomedical Information](https://mlsanity.com/paper/2304.09667/) (2023)
- [ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search](https://mlsanity.com/paper/2310.13227/) (2023)
- [WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences](https://mlsanity.com/paper/2306.07906/) (2023)
- [AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn](https://mlsanity.com/paper/2306.08640/) (2023)
- [CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update](https://mlsanity.com/paper/2312.10908/) (2023)

## Built on by (most cited first, 11 of 11)

- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [Alignment for Efficient Tool Calling of Large Language Models](https://mlsanity.com/paper/2503.06708/) (2025)
- [Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use](https://mlsanity.com/paper/2602.11541/) (2026)
- [Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation](https://mlsanity.com/paper/2411.00412/) (2024)
- [CCTU: A Benchmark for Tool Use under Complex Constraints](https://mlsanity.com/paper/2603.15309/) (2026)
- [TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents](https://mlsanity.com/paper/2602.19633/) (2026)
- [Scores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM Agents](https://mlsanity.com/paper/2607.27083/) (2026)
- [Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development](https://mlsanity.com/paper/2505.21898/) (2025)
- [FutureWeaver: Planning Test-Time Compute for Multi-Agent Systems with Modularized Collaboration](https://mlsanity.com/paper/2512.11213/) (2025)
- [OR-Toolformer: Modeling and Solving Operations Research Problems with Tool Augmented Large Language Models](https://mlsanity.com/paper/2510.01253/) (2025)
- [Learning from Research: Toward Lifelong Agent Harness Evolution](https://mlsanity.com/paper/2609.40169/) (2026)

## Abstract (arXiv)

Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, has been widely overlooked. This paper proposes a novel method for budget-constrained tool learning. Our approach involves creating a preferable plan under the budget constraint before utilizing the tools. This plan outlines the feasible tools and the maximum number of times they can be employed, offering a comprehensive overview of the tool learning process for large language models. This allows them to allocate the budget from a broader perspective. To devise the plan without incurring significant extra costs, we suggest initially estimating the usefulness of the candidate tools based on past experience. Subsequently, we employ dynamic programming to formulate the plan. Experimental results demonstrate that our method can be integrated with various tool learning methods, significantly enhancing their effectiveness under strict budget constraints.