Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Fusing Task-Oriented and Open-Domain Dialogues in Conversational Agents
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the whole dialogue history instead of only the latest user turn | BERT mode classifier · FusedChat mode classification | Accuracy: 0.993 -> 0.995 | Helped |
| Use a classification-based system instead of a two-in-one generator | FusedChat inter-mode dialogue models · FusedChat ODD-grounded TODs | Success: 56.9 -> 60.0 | Helped |
| Use a classification-based system instead of a two-in-one generator | FusedChat inter-mode dialogue models · FusedChat ODD-grounded TODs | Joint SA: 0.574 -> 0.584 | Helped |
| Use a classification-based system instead of a two-in-one generator | FusedChat inter-mode dialogue models · FusedChat TOD-grounded ODDs | SSA: 0.42 -> 0.48 | Helped |
| Use a classification-based system instead of a two-in-one generator | FusedChat inter-mode dialogue models · FusedChat TOD-grounded ODDs | PPL: 9.15 -> 8.79 | Helped |
| Use a classification-based system instead of a two-in-one generator | FusedChat inter-mode dialogue models · FusedChat full test set | Inform: 70.4 -> 75.1 | Helped |
| Evaluate on ODD-grounded TODs rather than vanilla TODs | Neural Pipeline · FusedChat ODD-grounded TODs versus MultiWOZ | Success: 64.3 -> 60.0 | Hurt |
| Use the classification-based model instead of the full method | FusedChat · All reported benchmarks | Multiple dialogue metrics | Mixed |
Closest papers by meaning
- Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal (AAAI 2024 · similarity 0.88)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.87)
- ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models (ICLR 2025 · similarity 0.87)
- Aligning Spoken Dialogue Models from User Interactions (ICML 2025 · similarity 0.86)
- Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models (NeurIPS 2024 · similarity 0.86)
- ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction (ICLR 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.