Rethinking Conversational Agents in the Era of LLMs: Proactivity, Non-collaborativity, and Beyond

Paper · Source
Conversational Agents

as LLMs are trained to follow users’ instructions, LLM-augmented conversational systems typically overlook the design of an essential property in intelligent conversations, i.e., goal awareness. In this tutorial, we will introduce the recent advances on the design of agent’s awareness of goals in a wide range of conversational systems, including proactive, non-collaborative, and multi-goal conversational systems.

Derived from the definition of proactivity in organizational behaviors [23] and its dictionary definitions, conversational agents’ proactivity can be defined as the capability to create or control the conversation by taking the initiative and anticipating impacts on themselves or human users.

Proactive ODD systems can consciously change topics [49] and lead directions [45, 48] for improving user engagement in the conversation. We will present the existing methods for topic shifting and planning in open-domain dialogues, including keyword-based discourse-level topic planning [45], graph-based topic planning [38, 52], and learning from interactions with users [28].

Synthesis notes that discuss concepts related to this paper 4

Notes in this collection most semantically related to the paper, ranked by cosine similarity.

Lines of inquiry this paper opens 24

Research framings built by reading the notes related to this paper — the questions it feeds into.

How faithfully do LLMs reflect their actual reasoning in outputs and explanations? How can language models sustain linguistic synchrony and intersubjectivity during dialogue? How should conversational agents balance goal-driven initiative with user control? How does AI assistance affect human cognitive development and reasoning autonomy? Why do multi-turn conversations degrade AI intent and coherence? When should tasks involve human-AI partnership versus full automation? Does RLHF training sacrifice accuracy and grounding for user agreement? How can LLM user simulators model realistic goal-driven conversation? How do interface design choices shape consciousness attribution? How should human oversight be integrated with autonomous AI systems? How should dialogue systems represent uncertainty from noisy speech input? How does objective evolution guide discovery better than fixed planning? How should memory consolidation strategies shape agent performance over time? What coordination failures limit multi-agent LLM systems as they scale? Why do LLM chatbots fail as independent therapeutic agents? Should GUI agents use structured representations instead of raw pixels? Why do language models reinforce false assumptions instead of correcting them?