# Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach

arXiv: https://arxiv.org/abs/2411.14484 · HTML: https://mlsanity.com/paper/2411.14484/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [LLM+P: Empowering Large Language Models with Optimal Planning Proficiency](https://mlsanity.com/paper/2304.11477/) (2023)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [NATURAL PLAN: Benchmarking LLMs on Natural Language Planning](https://mlsanity.com/paper/2406.04520/) (2024)
- [Chain of Thoughtlessness? An Analysis of CoT in Planning](https://mlsanity.com/paper/2405.04776/) (2024)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models](https://mlsanity.com/paper/2308.00675/) (2023)
- [NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions](https://mlsanity.com/paper/2405.04215/) (2024)
- [On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models](https://mlsanity.com/paper/2405.13966/) (2024)
- [P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task](https://mlsanity.com/paper/2409.11279/) (2024)
- [TorchOpera: A Compound AI System for LLM Safety](https://mlsanity.com/paper/2406.10847/) (2024)

## Built on by (most cited first, 9 of 9)

- [The Limits of Inference Scaling Through Resampling](https://mlsanity.com/paper/2411.17501/) (2024)
- [Large Language Models for Planning: A Comprehensive and Systematic Survey](https://mlsanity.com/paper/2505.19683/) (2025)
- [Foundation Models for CPS-IoT: Opportunities and Challenges](https://mlsanity.com/paper/2501.16368/) (2025)
- [Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions](https://mlsanity.com/paper/2503.02238/) (2025)
- [End-to-end PDDL Planning with Hardcoded and Dynamic Agents](https://mlsanity.com/paper/2512.09629/) (2025)
- [Towards Pervasive Distributed Agentic Generative AI -- A State of The Art](https://mlsanity.com/paper/2506.13324/) (2025)
- [Can Agents Secure Hardware? Evaluating Agentic LLM-Driven Obfuscation for IP Protection](https://mlsanity.com/paper/2604.13298/) (2026)
- [Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation](https://mlsanity.com/paper/2606.05268/) (2026)
- [Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions](https://mlsanity.com/paper/2609.19654/) (2026)

## Abstract (arXiv)

Previous work has attempted to boost Large Language Model (LLM) performance on planning and scheduling tasks through a variety of prompt engineering techniques. While these methods can work within the distributions tested, they are neither robust nor predictable. This limitation can be addressed through compound LLM architectures where LLMs work in conjunction with other components to ensure reliability. In this paper, we present a technical evaluation of a compound LLM architecture--the LLM-Modulo framework. In this framework, an LLM is paired with a complete set of sound verifiers that validate its output, re-prompting it if it fails. This approach ensures that the system can never output any fallacious output, and therefore that every output generated is guaranteed correct--something previous techniques have not been able to claim. Our results, evaluated across four scheduling domains, demonstrate significant performance gains with the LLM-Modulo framework using various models. Additionally, we explore modifications to the base configuration of the framework and assess their impact on overall system performance.