# NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models

arXiv: https://arxiv.org/abs/2510.09355 · HTML: https://mlsanity.com/paper/2510.09355/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 47 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (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)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [Grounded Adaptation for Zero-shot Executable Semantic Parsing](https://mlsanity.com/paper/2009.07396/) (2020)
- [On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)](https://mlsanity.com/paper/2401.02500/) (2024)
- [Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives](https://mlsanity.com/paper/2407.14962/) (2024)
- [CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing](https://mlsanity.com/paper/2210.07074/) (2022)
- [Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization](https://mlsanity.com/paper/2012.04276/) (2020)
- [SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions](https://mlsanity.com/paper/2307.01139/) (2023)
- [Exploring the True Potential: Evaluating the Black-box Optimization Capability of Large Language Models](https://mlsanity.com/paper/2404.06290/) (2024)
- [Exploiting Language Models as a Source of Knowledge for Cognitive Agents](https://mlsanity.com/paper/2310.06846/) (2023)
- [An Analysis and Comparison of ACT-R and Soar](https://mlsanity.com/paper/2201.09305/) (2022)
- [Generating Data for Symbolic Language with Large Language Models](https://mlsanity.com/paper/2305.13917/) (2023)
- [From Decision to Action in Surgical Autonomy: Multi-Modal Large Language Models for Robot-Assisted Blood Suction](https://mlsanity.com/paper/2408.07806/) (2024)
- [Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation](https://mlsanity.com/paper/2205.08675/) (2022)
- [Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making](https://mlsanity.com/paper/2408.09176/) (2024)
- [From Effectiveness to Efficiency: Uncovering Linguistic Bias in Large Language Model-based Code Generation](https://mlsanity.com/paper/2406.00602/) (2024)
- [Eliciting Problem Specifications via Large Language Models](https://mlsanity.com/paper/2405.12147/) (2024)

## Built on by (most cited first, 1 of 1)

- [Human Cognition in Machines: A Unified Perspective of World Models](https://mlsanity.com/paper/2604.16592/) (2026)

## Abstract (arXiv)

SOAR, a classic symbol-based cognitive architecture, has been fostering the development of general, human-like intelligent agents. Nevertheless, its practical adoption is hindered by the laborious manual rule coding. Emerging Large Language Models (LLMs) present the immense potential for efficient rules generation. However, there is a critical gap that current research predominantly focuses on conceptual frameworks and lacks robust experimental validation. To bridge this gap, we propose textitNatural textitLanguage to textitGenerative textitSymbolic Rules (NL2GenSym), a novel framework that integrates LLMs with SOAR to autonomously produce generative symbolic rules from natural language. Specifically, our framework introduces a novel Execution-Grounded Generator-Critic mechanism. The LLM-based Generator, guided by a Retrieval-Augmented Generation-accessed self-evolving domain knowledge base, proposes rules from natural language. Subsequently, these rules are immediately executed within the SOAR environment to rigorously validate their correctness. Based on this execution-grounded feedback, a reflective LLM-based Critic drives the iterative refinement of these rules. Experiments on our specialized Water Jug Problem (WJP) dataset, utilizing both Gemini and Qwen series models, validate the efficacy of our framework. It achieves a success rate over 86% in generating rules from natural language. Crucially, the framework also generates novel heuristic rules, reducing average decision cycles for solving the WJP to 1.98 times the optimal solution and 1/1000 of baseline methods. Additionally, our initial experiments show that NL2GenSym enables smaller-parameter models to achieve better performance than larger counterparts.