# An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation Orchestration

arXiv: https://arxiv.org/abs/2609.07152 · HTML: https://mlsanity.com/paper/2609.07152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 28 of 28)

- [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)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark](https://mlsanity.com/paper/2105.00071/) (2021)
- [Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning](https://mlsanity.com/paper/1704.03084/) (2017)
- [Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk](https://mlsanity.com/paper/2401.05033/) (2024)
- [Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers](https://mlsanity.com/paper/2506.00054/) (2025)
- [Towards LLM-driven Dialogue State Tracking](https://mlsanity.com/paper/2310.14970/) (2023)
- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs](https://mlsanity.com/paper/2303.08954/) (2023)
- [DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue](https://mlsanity.com/paper/2502.13847/) (2025)
- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [Dialog Flow Induction for Constrainable LLM-Based Chatbots](https://mlsanity.com/paper/2408.01623/) (2024)
- [Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.14528/) (2023)
- [Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs](https://mlsanity.com/paper/2503.08857/) (2025)
- [Deploying a Retrieval based Response Model for Task Oriented Dialogues](https://mlsanity.com/paper/2210.14379/) (2022)
- [NeuSymMS: A Hybrid Neuro-Symbolic Memory System for Persistent, Self-Curating LLM Agents](https://mlsanity.com/paper/2605.17596/) (2026)
- [ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2605.19077/) (2026)

## Abstract (arXiv)

Goal-oriented conversational systems must answer factual questions, understand visitor-provided information, and advance business objectives without becoming rigid questionnaires. This paper proposes a Symbolic-RAG-Generative architecture centered on the Goal-oriented Retrieval-Augmented Conversation Engine (GRACE). An instruction-constrained Business Goal Compiler transforms business intent into an immutable objective set, normalized priority vector, canonical questions, and initial state vector. At runtime, GRACE receives the complete conversation history, latest visitor message, current state, and grounded answer generated by a separate RAG component. It updates completion only from visitor-authored evidence and selects one contextually modulated follow-up. The core policy maximizes expected business progress subject to a minimum visitor-utility constraint. We formalize the state, monotonic transitions, source separation, question modulation, and constrained policy; present the reference architecture; and define an evaluation comprising 24 English real-estate and 10 Spanish professional-cleaning conversations, totaling 119 protocol-defined visitor turns. Across both domains, GRACE achieves 84.9% exact state-transition accuracy, 91.6% evidence precision, 89.6% evidence recall, 100% monotonicity, and 94.1% terminal-state accuracy. The evaluation establishes compelling symbolic-state performance across standard, multi-goal, RAG-detour, validation, refusal, and robustness scenarios.