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.

Is language model reasoning authentic and what causes models to reason? What prevents conversational agents from taking initiative in dialogue? What determines appropriate intervention timing and manner for AI agents? When should work require human-AI partnership versus full automation? Does preference optimization systematically degrade conversational grounding in language models? Do language models reason like humans or mimic surface patterns? How do multi-agent LLM systems fail distinctly compared to single agents? How can humans maintain meaningful oversight as AI systems become increasingly autonomous and complex? What mechanisms preserve shared understanding in evolving conversations? What fundamental constraints limit how effectively agents can improve themselves? How should agents manage memory granularity to improve long-term performance? How can AI chatbots provide therapeutic benefit without causing harm? Should AI communication design follow human conversation norms or develop distinct machine-specific principles? Should GUI agents use structured representations over raw visual input? Do language models learn genuine understanding or just surface patterns?