# Large Language Models Are Neurosymbolic Reasoners arXiv: https://arxiv.org/abs/2401.09334 ยท HTML: https://mlsanity.com/paper/2401.09334/ ## Key facts - Cited by 31 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 8 of its 49 references that are in the map. - First posted on arXiv 17 Jan 2024. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 8 of 8) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023) - [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013) - [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022) - [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023) - [Counting to Explore and Generalize in Text-based Games](https://mlsanity.com/paper/1806.11525/) (2018) - [Large Language Models can Implement Policy Iteration](https://mlsanity.com/paper/2210.03821/) (2022) ## Built on by (most cited first, 30 of 31) - [ATLaS: Agent Tuning via Learning Critical Steps](https://mlsanity.com/paper/2503.02197/) (2025) - [Monte Carlo Planning with Large Language Model for Text-Based Game Agents](https://mlsanity.com/paper/2504.16855/) (2025) - [MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation](https://mlsanity.com/paper/2411.17636/) (2024) - [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024) - [Towards Rationality in Language and Multimodal Agents: A Survey](https://mlsanity.com/paper/2406.00252/) (2024) - [Jailbreaking Large Language Models with Symbolic Mathematics](https://mlsanity.com/paper/2409.11445/) (2024) - [NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains](https://mlsanity.com/paper/2503.00870/) (2025) - [Large Language Models are Zero-Shot Recognizers for Activities of Daily Living](https://mlsanity.com/paper/2407.01238/) (2024) - [The Sociolinguistic Foundations of Language Modeling](https://mlsanity.com/paper/2407.09241/) (2024) - [GraphEval36K: Benchmarking Coding and Reasoning Capabilities of Large Language Models on Graph Datasets](https://mlsanity.com/paper/2406.16176/) (2024) - [Incentivizing Strong Reasoning from Weak Supervision](https://mlsanity.com/paper/2505.20072/) (2025) - [Large Language Models are Interpretable Learners](https://mlsanity.com/paper/2406.17224/) (2024) - [Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs](https://mlsanity.com/paper/2411.18564/) (2024) - [RuAG: Learned-rule-augmented Generation for Large Language Models](https://mlsanity.com/paper/2411.03349/) (2024) - [Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models](https://mlsanity.com/paper/2401.11725/) (2024) - [Self-evolving LLM agents with in-distribution Optimization](https://mlsanity.com/paper/2606.07367/) (2026) - [Enhancing Conflict Resolution in Language Models via Abstract Argumentation](https://mlsanity.com/paper/2412.16725/) (2024) - [SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence](https://mlsanity.com/paper/2512.22334/) (2025) - [Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis](https://mlsanity.com/paper/2509.07122/) (2025) - [A Survey on the Integration of Generative AI for Critical Thinking in Mobile Networks](https://mlsanity.com/paper/2404.06946/) (2024) - [Parameter Choice and Neuro-Symbolic Approaches for Deep Domain-Invariant Learning](https://mlsanity.com/paper/2410.06235/) (2024) - [Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving](https://mlsanity.com/paper/2510.00919/) (2025) - [Say Anything but This: When Tokenizer Betrays Reasoning in LLMs](https://mlsanity.com/paper/2601.14658/) (2026) - [MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation](https://mlsanity.com/paper/2602.16898/) (2026) - [Unsupervised multiple choices question answering via universal corpus](https://mlsanity.com/paper/2402.17333/) (2024) - [Model-Grounded Symbolic Artificial Intelligence Systems Learning and Reasoning with Model-Grounded Symbolic Artificial Intelligence Systems](https://mlsanity.com/paper/2507.09854/) (2025) - [Enabling Fine-Grained Operating Points for Black-Box LLMs](https://mlsanity.com/paper/2510.17727/) (2025) - [ID-LoRA: Efficient Low-Rank Adaptation Inspired by Matrix Interpolative Decomposition](https://mlsanity.com/paper/2602.20727/) (2026) - [Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning](https://mlsanity.com/paper/2603.12953/) (2026) - [Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems](https://mlsanity.com/paper/2605.16286/) (2026) ## Abstract (arXiv) A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning. This paper investigates the potential application of Large Language Models (LLMs) as symbolic reasoners. We focus on text-based games, significant benchmarks for agents with natural language capabilities, particularly in symbolic tasks like math, map reading, sorting, and applying common sense in text-based worlds. To facilitate these agents, we propose an LLM agent designed to tackle symbolic challenges and achieve in-game objectives. We begin by initializing the LLM agent and informing it of its role. The agent then receives observations and a set of valid actions from the text-based games, along with a specific symbolic module. With these inputs, the LLM agent chooses an action and interacts with the game environments. Our experimental results demonstrate that our method significantly enhances the capability of LLMs as automated agents for symbolic reasoning, and our LLM agent is effective in text-based games involving symbolic tasks, achieving an average performance of 88% across all tasks.