# Unlocking Proactivity in Task-Oriented Dialogue

arXiv: https://arxiv.org/abs/2605.22240 · HTML: https://mlsanity.com/paper/2605.22240/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 21 May 2026.

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

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks](https://mlsanity.com/paper/2503.15478/) (2025)
- [Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward](https://mlsanity.com/paper/2504.03206/) (2025)
- [KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning](https://mlsanity.com/paper/2211.16773/) (2022)
- [UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2601.09215/) (2026)
- [Task-Oriented Dialogue with In-Context Learning](https://mlsanity.com/paper/2402.12234/) (2024)
- [SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue](https://mlsanity.com/paper/2602.03548/) (2026)
- [Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue](https://mlsanity.com/paper/2602.22697/) (2026)

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

- [Proactive Dialogue Policy Optimization via Cognitive-State Transition](https://mlsanity.com/paper/2609.34948/) (2026)

## Abstract (arXiv)

Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that actively probes the user's concerns and steers the conversation toward acceptance within a bounded number of turns. Yet post-trained LLMs are inherently conservative, and reward-shaping RL (e.g., GRPO) struggles since it only re-weights what an already passive policy samples. We show that conditioning on the user's latent concerns unlocks proactive capability that no amount of sampling can undermine, establishing these concerns as a pivotal training-time signal. To operationalize this finding, we build the Cognitive User Simulator, which models each user as a stratified persona comprising observable external traits and hidden internal concerns. The simulator produces faithful and diverse interactions, while emitting per-turn state dynamics that track persuasion progress. We then introduce Simulator-Induced Asymmetric-View Policy Optimization, which converts the modeled concerns and the simulation state transition into complementary training objectives: (1) Asymmetric On-Policy Self-Distillation that transfers concern-aware behavior from a privileged view of the same policy into its deployable, conversation-only view; and (2) State-Transition Policy Refinement ...