mlsanityData to 13 Oct 2026

LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators

arXiv 2512.18360 ↗First posted 20 Dec 2025cs.CL cs.AIcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

We present a novel neurosymbolic framework for RDF-to-text generation, in which the model is "trained" through collaborative interactions among multiple LLM agents rather than traditional backpropagation. The LLM agents produce rule-based Python code for a generator for the given domain, based on RDF triples only, with no in-domain human reference texts. The resulting system is fully interpretable, requires no supervised training data, and generates text nearly instantaneously using only a single CPU. Our experiments on the WebNLG and OpenDialKG data show that outputs produced by our approach reduce hallucination, with only slight fluency penalties compared to finetuned or prompted language models

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 15 of its 50 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

15 of 50 references.

References · 15

  1. 2024The Llama 3 Herd of Modelscited by 14,486
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,205
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,884
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,480
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,156
  6. 2024A Survey on LLM-as-a-Judgecited by 1,399
  7. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,200
  8. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 819
  9. 2020A Survey on Neural Network Interpretabilitycited by 291
  10. 2017Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluationcited by 206
  11. 2021JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphscited by 58
  12. 2023Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphscited by 24
3 more
  1. 2022Neural Pipeline for Zero-Shot Data-to-Text Generationcited by 19
  2. 2024Unifying Structured Data as Graph for Data-to-Text Pre-Trainingcited by 13
  3. 2025Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Multi-Agent LLM Judge: automatic personalized LLM judge design for evaluating natural language generation applications
  2. 2025NL2GenSym: Natural Language to Generative Symbolic Rules for SOAR Cognitive Architecture via Large Language Models
  3. 2025LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
  4. 2024LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration
  5. 2024Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
  6. 2024Offline Training of Language Model Agents with Functions as Learnable Weights
  7. 2023Automating Knowledge Acquisition for Content-Centric Cognitive Agents Using LLMs
  8. 2024MEGAnno+: A Human-LLM Collaborative Annotation System