Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents

• URL: http://arxiv.org/abs/2511.08835v1
• Date: Thu, 13 Nov 2025 01:10:37 GMT
• Title: Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents
• Authors: Yejin Yoon, Yuri Son, Namyoung So, Minseo Kim, Minsoo Cho, Chanhee Park, Seungshin Lee, Taeuk Kim,
• Abstract summary: We introduce TACT (TOD-And-Chitchat Transition), a dataset designed for transition-aware dialogue modeling.<n>TACT supports both user- and agent-driven mode switches, enabling robust modeling of complex conversational dynamics.<n>Models trained on TACT outperform baselines in both intent detection and mode transition handling.
• Score: 9.57795435306441
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between these modes. To address this gap, we introduce TACT (TOD-And-Chitchat Transition), a dataset designed for transition-aware dialogue modeling that incorporates structurally diverse and integrated mode flows. TACT supports both user- and agent-driven mode switches, enabling robust modeling of complex conversational dynamics. To evaluate an agent's ability to initiate and recover from mode transitions, we propose two new metrics -- Switch and Recovery. Models trained on TACT outperform baselines in both intent detection and mode transition handling. Moreover, applying Direct Preference Optimization (DPO) to TACT-trained models yields additional gains, achieving 75.74\% joint mode-intent accuracy and a 70.1\% win rate against GPT-4o in human evaluation. These results demonstrate that pairing structurally diverse data with DPO enhances response quality and transition control, paving the way for more proactive and transition-aware conversational agents.

Related papers

• Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning [66.52010873968383]
  We introduce a conversational agent that interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through reinforcement learning (RL) training.<n>The experimental results across four widely used conversational benchmarks demonstrate the effectiveness of our methods.
  arXiv  Detail & Related papers  (2026-01-19T14:55:54Z)
• Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation [21.732611237889326]
  Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing.<n>Recent works employ reinforcement learning to enhance traditional approaches through a more effective trial-and-error way.<n>We propose a novel heterogeneous multi-agent RL framework to enable cooperative and scalable feature transformation.
  arXiv  Detail & Related papers  (2025-11-26T21:45:38Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction [77.62279834617475]
  We propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure.<n>Our method focuses on two key directions: (1) Next-Agent Prediction, which selects the most suitable agent role at each step, and (2) Next-Context Selection, which enables each agent to selectively access relevant information from any previous step.
  arXiv  Detail & Related papers  (2025-06-21T18:34:43Z)
• Proactive Guidance of Multi-Turn Conversation in Industrial Search [38.18559057329515]
  We propose a novel two-phase framework to provide proactive guidance.<n>Goal-adaptive Supervised Fine-Tuning (G-SFT) provides goal-relevant contextual information.<n>Click-oriented Reinforcement Learning (C-RL) constructs preference pairs from user click signals, and proactively improves click-through rates.
  arXiv  Detail & Related papers  (2025-05-30T06:16:30Z)
• Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities [93.09944267871163]
  FullDuplexBench is a benchmark that systematically evaluates key interactive behaviors.<n>By releasing our benchmark code we aim to advance spoken dialogue modeling and the development of more natural and engaging SDMs.
  arXiv  Detail & Related papers  (2025-03-06T18:59:16Z)
• AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations [57.99479708224221]
  We propose a novel framework called AIMDiT to solve the problem of multimodal fusion of deep features. Experiments conducted using our AIMDiT framework on the public benchmark dataset MELD reveal 2.34% and 2.87% improvements in terms of the Acc-7 and w-F1 metrics.
  arXiv  Detail & Related papers  (2024-04-12T11:31:18Z)
• Dialog Action-Aware Transformer for Dialog Policy Learning [22.262659702998892]
  We propose to make full use of the plain text knowledge from the pre-trained language model to accelerate the RL agent's learning speed. Specifically, we design a dialog action-aware transformer encoder (DaTrans) which integrates a new fine-tuning procedure named masked last action task. DaTrans is further optimized in an RL setting with ongoing interactions and evolves through exploration in the dialog action space toward maximizing long-term accumulated rewards.
  arXiv  Detail & Related papers  (2023-09-05T13:47:25Z)
• System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator [4.714297769572548]
  We study dialogue scenarios that start from chit-chat but eventually switch to task-related services. A unified dialogue model, which can engage in both chit-chat and task-oriented dialogues, takes the initiative during the dialogue mode transition.
  arXiv  Detail & Related papers  (2023-08-06T12:25:22Z)
• Meta Dialogue Policy Learning [58.045067703675095]
  We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains. We decompose the state and action representation space into feature subspaces corresponding to these low-level components. In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency.
  arXiv  Detail & Related papers  (2020-06-03T23:53:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.