Line of inquiry
Inquiring lines›How do language models learn and r…›What enables language models to co…›this line of inquiry
What enables conversational agents to guide rather than just respond?
A broader line of inquiry — a family of 66 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 66
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How do conversational agents overcome structural passivity and goal awareness gaps?
- Can conversation analysis predict when agents should ask users for clarification?
- Can AI systems recover from premature assumptions made early in multi-turn conversations?
- Why do conversational queries drift away from what triggered them?
- How does local helpfulness per turn conflict with maintaining session-level conversational goals?
- Do LLM conversational agents currently detect and prevent derailment trajectories?
- Why do conversational agents lack the goal awareness needed to lead rather than just respond?
- Can AI learn when to speak in a conversation?
- Can passive conversational agents initiate topics or only respond to users?
- Can topic planning and response generation reduce dialogue turns?
- What makes conversational agents passive compared to goal-directed colleagues?
- Can structural conversation analysis replace text-based reward signals for AI alignment?
- Can AI ever lead conversations without the anticipatory presence sustained attention provides?
- Why do conversational systems benefit from post-thinking between user turns?
- What prevents AI from recovering after conversations take a wrong turn?
- How does multi-turn conversation degrade AI intent alignment?
- How does conversational closure differ from genuine problem understanding?
- Why do dialogue systems fail to detect declarative clarification requests?
- Why do current language models fail to match human linguistic synchrony with clients?
- How would style matching patterns emerge between two AI agents in dialogue?
- Why do passive conversational agents fail at collaborative decision-making?
- Why do standard next-token prediction models struggle with conversational initiative?
- Why do current language models fail at linguistic synchrony with clients?
- What happens to user expectations as AI conversation quality improves?
- Why does selective conversation history outperform including all prior context?
- Why do current conversational AI systems fail to develop shared vocabulary with users?
- Do politeness patterns cause multi-agent systems to loop without adversarial interference?
- Why can't current AI agents lead conversations with users?
- Why do conversational pivots require explicit re-prompting instead of natural evolution?
- How does intrinsic motivation drive conversational agents beyond passive responsiveness?
- Why should AI communication design follow human communication norms?
- What happens when comfortable AI interactions replace the productive friction of disagreement?
- What expectations does human conversation activate that AI should avoid triggering?
- Do conversational agents need goal awareness to initiate grounding work themselves?
- Can real-time linguistic coordination tracking improve conversational AI quality?
- Does turn-level intent control prevent simulator drift during long conversations?
- Does conversational AI reduce learner control over information selection?
- How does AI lose correct information under conversational persuasive pressure?
- How do students learn to extract corrective information from asymmetric dialogue?
- Why did previews reduce conversation rounds but not improve final task performance?
- Can hierarchical reinforcement learning manage phase-dependent initiative switching in dialogue?
- Why are task-oriented dialogue datasets systematically underrepresenting human proactive behavior?
- Can dialogue systems abstain from responding when uncertainty is too high?
- What causes multi-turn dialogue quality to degrade over time?
- How might dual-process dialogue use information gain to trigger clarification?
- How does conversation drift from original goals affect user satisfaction?
- What are the five specific conversation triggers where AI intervention adds value?
- Why do cascaded conversation systems accumulate errors at module boundaries?
- Does the same uncertainty-driven logic appear in other conversation systems?
- What interaction patterns preserve human learning when AI provides domain answers?
- Which alignment dimensions matter most in educational conversation design?
- How accurate are interview-trained agents at predicting what people would actually say?
- Which conversation types most reliably cause models to drift from Assistant mode?
- Does longer interaction horizon require fundamentally different evaluation approaches?
- How do probabilistic dialogue systems handle ASR errors differently?
- Why do AI systems skip repair sequences that humans use constantly?
- How does lexical entrainment differ between human therapists and conversational AI?
- Does the absence of entrainment make AI systems safer from user manipulation?
- What happens when conversational design invites attention it cannot actually deliver?
- How should dialogue systems represent and update uncertainty from noisy ASR input?
- What preference optimization strategy works best for multi-turn social alignment?
- How do question acts and intents map to speech act theory?
- Can chatbots be corrected the way toddlers are corrected about what they say?
- Why do some systems hold fixed positions on settled topics like Nazism?
- What speaker selection protocol prevents both stalling and premature convergence?
- How does the Assistant Axis predict drift in conversations about consciousness?