Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems
On the map: Deep reinforcement learning methods → RL training of language and agent models
Abstract (arXiv)
Post-processing networks (PPNs) are components that modify the outputs of arbitrary modules in task-oriented dialogue systems and are optimized using reinforcement learning (RL) to improve the overall task completion capability of the system. However, previous PPN-based approaches have been limited to handling only a subset of modules within a system, which poses a significant limitation in improving the system performance. In this study, we propose a joint optimization method for post-processing the outputs of all modules using universal post-processing networks (UniPPNs), which are language-model-based networks that can modify the outputs of arbitrary modules in a system as a sequence-transformation task. Moreover, our RL algorithm, which employs a module-level Markov decision process, enables fine-grained value and advantage estimation for each module, thereby stabilizing joint learning for post-processing the outputs of all modules. Through both simulation-based and human evaluation experiments using the MultiWOZ dataset, we demonstrated that UniPPN outperforms conventional PPNs in the task completion capability of task-oriented dialogue systems.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. First posted on arXiv 2 Feb 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Improving Multi-Domain Task-Oriented Dialogue System with Offline Reinforcement Learning
- 2020Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems
- 2024Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability
- 2025An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals
- 2026Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models
- 2024Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
- 2025Towards a Unified View of Large Language Model Post-Training
- 2026Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models