# RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

arXiv: https://arxiv.org/abs/2601.00086 · HTML: https://mlsanity.com/paper/2601.00086/

## Key facts

- Cited by 2 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 25 of its 102 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## 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, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities](https://mlsanity.com/paper/2408.07666/) (2024)
- [ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings](https://mlsanity.com/paper/2305.11554/) (2023)
- [Self-Discover: Large Language Models Self-Compose Reasoning Structures](https://mlsanity.com/paper/2402.03620/) (2024)
- [ToolGen: Unified Tool Retrieval and Calling via Generation](https://mlsanity.com/paper/2410.03439/) (2024)
- [ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://mlsanity.com/paper/2501.02506/) (2025)
- [Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus](https://mlsanity.com/paper/2411.12498/) (2024)
- [Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs](https://mlsanity.com/paper/2402.11442/) (2024)
- [Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data](https://mlsanity.com/paper/2305.19912/) (2023)
- [Customizing Language Model Responses with Contrastive In-Context Learning](https://mlsanity.com/paper/2401.17390/) (2024)
- [Symbolic Working Memory Enhances Language Models for Complex Rule Application](https://mlsanity.com/paper/2408.13654/) (2024)
- [Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use](https://mlsanity.com/paper/2509.12867/) (2025)
- [AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning](https://mlsanity.com/paper/2506.15651/) (2025)
- [RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering](https://mlsanity.com/paper/2410.22353/) (2024)
- [SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt Optimization](https://mlsanity.com/paper/2402.11347/) (2024)
- [ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools](https://mlsanity.com/paper/2510.00023/) (2025)
- [Improving In-Context Learning with Reasoning Distillation](https://mlsanity.com/paper/2504.10647/) (2025)

## Built on by (most cited first, 2 of 2)

- [Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use](https://mlsanity.com/paper/2602.20426/) (2026)
- [Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text](https://mlsanity.com/paper/2605.29076/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows. This highlights the need for effective adaptation to task-specific tools. We propose RIMRULE, a neuro-symbolic approach for LLM adaptation based on dynamic rule injection. Compact, interpretable rules are distilled from failure traces and injected into the prompt during inference to improve task performance. These rules are proposed by the LLM itself and consolidated using a Minimum Description Length (MDL) objective that favors generality and conciseness. Each rule is stored in both natural language and a structured symbolic form, supporting efficient retrieval at inference time. Experiments on tool-use benchmarks show that this approach improves accuracy on both seen and unseen tools without modifying LLM weights. It outperforms prompting-based adaptation methods and complements finetuning. Moreover, rules learned from one LLM can be reused to improve others, including long reasoning LLMs, highlighting the portability of symbolic knowledge across architectures.