# TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

arXiv: https://arxiv.org/abs/2401.12869 · HTML: https://mlsanity.com/paper/2401.12869/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action](https://mlsanity.com/paper/2303.11381/) (2023)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning](https://mlsanity.com/paper/2209.14610/) (2022)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [LEVER: Learning to Verify Language-to-Code Generation with Execution](https://mlsanity.com/paper/2302.08468/) (2023)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning](https://mlsanity.com/paper/2006.08381/) (2020)
- [CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets](https://mlsanity.com/paper/2309.17428/) (2023)
- [Natural Language to Code Translation with Execution](https://mlsanity.com/paper/2204.11454/) (2022)
- [HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation](https://mlsanity.com/paper/2108.06712/) (2021)
- [LEGO-Prover: Neural Theorem Proving with Growing Libraries](https://mlsanity.com/paper/2310.00656/) (2023)
- [AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn](https://mlsanity.com/paper/2306.08640/) (2023)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [Top-Down Synthesis for Library Learning](https://mlsanity.com/paper/2211.16605/) (2022)
- [LILO: Learning Interpretable Libraries by Compressing and Documenting Code](https://mlsanity.com/paper/2310.19791/) (2023)
- [Modular Visual Question Answering via Code Generation](https://mlsanity.com/paper/2306.05392/) (2023)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Program Synthesis and Semantic Parsing with Learned Code Idioms](https://mlsanity.com/paper/1906.10816/) (2019)

## Built on by (most cited first, 30 of 75)

- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [Agent Workflow Memory](https://mlsanity.com/paper/2409.07429/) (2024)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills](https://mlsanity.com/paper/2504.07079/) (2025)
- [Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution](https://mlsanity.com/paper/2505.20286/) (2025)
- [Inducing Programmatic Skills for Agentic Tasks](https://mlsanity.com/paper/2504.06821/) (2025)
- [How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://mlsanity.com/paper/2505.16067/) (2025)
- [SciAgent: Tool-augmented Language Models for Scientific Reasoning](https://mlsanity.com/paper/2402.11451/) (2024)
- [SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents](https://mlsanity.com/paper/2508.02085/) (2025)
- [AutoPresent: Designing Structured Visuals from Scratch](https://mlsanity.com/paper/2501.00912/) (2025)
- [HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale](https://mlsanity.com/paper/2409.16299/) (2024)
- [SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios](https://mlsanity.com/paper/2512.18470/) (2025)
- [What Are Tools Anyway? A Survey from the Language Model Perspective](https://mlsanity.com/paper/2403.15452/) (2024)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments](https://mlsanity.com/paper/2402.14672/) (2024)
- [ReGAL: Refactoring Programs to Discover Generalizable Abstractions](https://mlsanity.com/paper/2401.16467/) (2024)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (2025)
- [UItron: Foundational GUI Agent with Advanced Perception and Planning](https://mlsanity.com/paper/2508.21767/) (2025)
- [RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving](https://mlsanity.com/paper/2505.21577/) (2025)
- [How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations](https://mlsanity.com/paper/2510.22780/) (2025)
- [A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2605.07358/) (2026)
- [SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning](https://mlsanity.com/paper/2605.09423/) (2026)
- [Toward Efficient Agents: Memory, Tool learning, and Planning](https://mlsanity.com/paper/2601.14192/) (2026)
- [PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables](https://mlsanity.com/paper/2412.04272/) (2024)
- [ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory](https://mlsanity.com/paper/2510.06664/) (2025)
- [From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking](https://mlsanity.com/paper/2506.19724/) (2025)
- [Benchmarking Failures in Tool-Augmented Language Models](https://mlsanity.com/paper/2503.14227/) (2025)
- [Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models](https://mlsanity.com/paper/2506.06137/) (2025)
- [User as Code: Executable Memory for Personalized Agents](https://mlsanity.com/paper/2606.16707/) (2026)
- [ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning](https://mlsanity.com/paper/2510.07768/) (2025)

## Abstract (arXiv)

Language models (LMs) can solve tasks such as answering questions about tables or images by writing programs. However, using primitive functions often leads to verbose and error-prone programs, and higher-level functions require expert design. To enable better solutions without human labor, we ask code LMs to curate reusable high-level functions, and use them to write solutions. We present TROVE, a training-free method of inducing a verifiable and efficient toolbox of functions, by generating via using, growing, and periodically trimming the toolbox. On 11 datasets from math, table question answering, and image reasoning tasks, TROVE consistently yields simpler solutions with higher accuracy than baselines using CODELLAMA and previous methods using GPT, while using 79-98% smaller toolboxes. TROVE further enables 31% faster and 13% more accurate human verification than baselines. With the same pipeline, it creates diverse functions for varied tasks and datasets, providing insights into their individual characteristics.