Back to AI Lab

Dialogue

Research papers, repositories, and articles about dialogue

Showing 4 of 4 items

TIME: Temporally Intelligent Meta-reasoning Engine for Context Triggered Explicit Reasoning

TIME teaches dialogue models to drop short "thinking" blocks only when time gaps or context shifts actually demand deeper reasoning. Models keep answers compact while still reasoning hard when conversations get tricky or span days instead of seconds.

Susmit Das

SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning

Argues that current task-oriented agents are over-optimized as passive followers and under-use conversation as an action. SpeakRL introduces a reinforcement-learning setup that rewards models for asking clarifying questions when the user’s intent is ambiguous, balancing ‘asking’ vs ‘acting’. On synthetic task-oriented dialogue scenarios, the trained agents substantially improve task completion rates without bloating the number of turns, suggesting that proactive clarification is a powerful, underused control knob.

Emre Can Acikgoz, Jinoh Oh

MAPO: Mixed Advantage Policy Optimization for Long-Horizon Multi-Turn Dialogue

Introduces a new optimization rule for training chat agents over long conversations. The goal: steadier learning and more helpful dialogue without exploding token and compute costs.

Naifan Zhang, Ruihan Sun

MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations

Proposes a multi‑agent architecture where specialized conversational agents coordinate to decide when and how to ask clarification questions in ambiguous multi‑turn tasks. Instead of a monolithic assistant, MAC assigns roles and coordination rules so that the ‘right’ agent takes the lead on resolving uncertainty. This is a nice complement to SpeakRL: one focuses on *whether* to clarify, the other on *who* clarifies and how to coordinate in complex workflows.

Emre Can Acikgoz, Jinoh Oh