A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions

TL;DR

The paper envisions a desideratum for next-generation Conversational Agents organized around three core dimensions: Reasoning, Monitor, and Control. It surveys a broad set of methods—ranging from Chain-of-Thought and Tree of Thoughts to ReAct and MCTS-based tool use—while detailing self-awareness, user-state tracking, and policy adherence as critical monitoring and control components. By articulating a taxonomy and outlining a forward-looking roadmap, the authors identify key gaps such as long-term multi-turn reasoning, self-evolution, personalization, and proactive collaboration, and they propose directions including realistic evaluation, multi-agent collaboration, and multimodal expansion. The work provides a structured foundation intended to guide future research toward more capable, robust, and potentially AGI-aligned Conversational Agents, complemented by a curated repository of relevant papers.

Abstract

Recent advances in Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users. Yet, fundamental questions about their capabilities, limitations, and paths forward remain open. This survey paper presents a desideratum for next-generation Conversational Agents - what has been achieved, what challenges persist, and what must be done for more scalable systems that approach human-level intelligence. To that end, we systematically analyze LLM-driven Conversational Agents by organizing their capabilities into three primary dimensions: (i) Reasoning - logical, systematic thinking inspired by human intelligence for decision making, (ii) Monitor - encompassing self-awareness and user interaction monitoring, and (iii) Control - focusing on tool utilization and policy following. Building upon this, we introduce a novel taxonomy by classifying recent work on Conversational Agents around our proposed desideratum. We identify critical research gaps and outline key directions, including realistic evaluations, long-term multi-turn reasoning skills, self-evolution capabilities, collaborative and multi-agent task completion, personalization, and proactivity. This work aims to provide a structured foundation, highlight existing limitations, and offer insights into potential future research directions for Conversational Agents, ultimately advancing progress toward Artificial General Intelligence (AGI). We maintain a curated repository of papers at: https://github.com/emrecanacikgoz/awesome-conversational-agents.

Figures (2)

• Figure 1: Overview of a Conversational Agent illustrating proposed desideratum.
• Figure 2: A taxonomy of our desiderata for Conversational Agents, with representative approaches listed for each component.