# Bridging Reasoning and Action: Hybrid LLM-RL Framework for Efficient Cross-Domain Task-Oriented Dialogue

arXiv: https://arxiv.org/abs/2604.23345 · HTML: https://mlsanity.com/paper/2604.23345/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 6 of 6)

- [Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning](https://mlsanity.com/paper/2305.13660/) (2023)
- [ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems](https://mlsanity.com/paper/2002.04793/) (2020)
- [A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding](https://mlsanity.com/paper/2304.04256/) (2023)
- [LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2503.21807/) (2025)
- [TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities](https://mlsanity.com/paper/2407.21693/) (2024)
- [Graph Neural Network Policies and Imitation Learning for Multi-Domain Task-Oriented Dialogues](https://mlsanity.com/paper/2210.05252/) (2022)

## Abstract (arXiv)

Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn actions. Large language models (LLMs) can infer such constraints but are unreliable over long horizons, while Reinforcement learning (RL) optimizes long-horizon behavior yet cannot recover constraints from raw dialogue. Naively coupling LLMs with RL is therefore brittle: unverified or unstructured LLM outputs can corrupt state representations and misguide policy learning. Motivated by this, we propose Verified LLM-Knowledge empowered RL (VLK-RL), a hybrid framework that makes LLM-derived constraint reasoning usable for RL. VLK-RL first elicits candidate constraints with an LLM and then verifies them via a dual-role cross-examination procedure to suppress hallucinations and cross-turn inconsistencies. The verified constraints are mapped into ontology-aligned slot-value representations, yielding a structured, constraint-aware state for RL policy optimization. Experiments across multiple benchmarks demonstrate that VLK-RL significantly improves generalization and robustness, outperforming strong single-model baselines on long-horizon tasks.