On October 23, the iRTE2026 Real-Time Intelligence Conference was held in Beijing. Zhao Bin, founder and CEO of Agora, delivered a keynote speech titled "Conversational AGI: The Next Chapter of Real-Time Engagement" at the main forum, reviewing the key changes over the past year in real-time engagement, conversational AI, and underlying infrastructure, and proposing a "Five-Level Conversational Capability" framework that outlines the evolution path of conversational AI from basic question answering to deep understanding and relational communication.
Zhao Bin believes that as AI moves from answering questions to sustained conversation, understanding context, and executing tasks, real-time engagement is expanding from person-to-person to human-to-Agent interaction. The role of real-time engagement technology is also extending accordingly: it must not only make information transmission more stable and smooth, but also provide real-time support for AI's perception, understanding, expression, and action.
From "One Question, One Answer" to Deep Relational Communication: The Five-Level Evolution of Conversational AGI
In Zhao Bin's view, the progress of conversational AI should not be measured only by response speed and language naturalness. More importantly, whether it can understand the intent, situation, and relationships of its conversation partner, express itself appropriately in complex scenarios, and gradually form long-term, deep understanding.
Based on this judgment, Zhao Bin proposed in his speecha "Five-Level Conversational Capability" framework, dividing conversational capability into five levels:
L1:Expression based on one's own perspective: mainly self-expression and passive continuation, achieving "one question, one answer."
L2:Expression based on interaction patterns: moving from passive response to active expression, making conversation more natural and coherent.
L3:Communication based on individual cognition: understanding an individual's identity, intent, and situation, achieving communication tailored to each person.
L4:Communication based on group cognition: understanding social relationships and role differences, adapting to complex multi-party communication scenarios.
L5:Communication based on deep relationships: understanding long-term context and relationship evolution, forming deeper understanding and mental rapport, moving communication from understanding the present moment to understanding a person.
These five levels demonstrate not only the step-by-step enhancement of conversational technology, but also the change in the relationship between AI and humans: from completing a round of Q&A, to understanding a person, then to understanding relationships between people, and finally forming deep communication that transcends time and context.
Zhao Bin pointed out that conversational AI is developing from early passive, turn-taking interaction toward more proactive, more natural full-duplex conversation, and is beginning to try to understand people's personality, situation, emotions, and relationships. Looking ahead, AI also needs to break through role division and communication order in complex social scenarios, and further understand the long-term accumulated context of individuals. This is also an important development direction for conversational AGI: AI should not only understand a sentence, but also understand a person's true intent in the complete context and respond appropriately.
Real-Time AI Infra: The Key Infrastructure Supporting Conversational AGI
The continuous evolution of conversational capability also places higher demands on underlying technology.
Zhao Bin mentioned in his speech that over the past year, deep adoption of WebRTC technology by OpenAI and other companies has driven broader attention to and application of real-time engagement technology in the field of conversational AI. As AI moves from single-turn Q&A to sustained interaction,real-time engagement infrastructureis becoming an important technical pillar connecting models, agent runtime frameworks, and users.
Compared with traditional AI applications, conversational scenarios have stricter requirements for latency, stability, and two-way interaction. AI needs to receive user input while understanding context and organizing responses, handle interruptions at any time when necessary, and continuously invoke tools and advance tasks. Any noticeable delay in any link may break the naturalness of the conversation, or even affect whether tasks can be completed.
To support these needs, Zhao Bin introduced an infrastructure direction for real-time intelligent interaction: through a global real-time transmission network, distributed cloud-edge-device joint inference, real-time orchestration, and full-duplex interaction capabilities, models and Agents can collaborate continuously in real-world scenarios. Agora's conversational AI engine also centers on full-duplex interaction, connecting models, Agent runtime frameworks, and users to support a stable, synchronized real-time conversational experience.
Meanwhile, Lei Feng Network (WeChat account: 雷峰网) learned that Agora continues to improve conversational AI development tools and development kits for developers, combining SDKs, Skills, CLI tools, Recipes, and other capabilities to help developers build Agents with complete logic and execution capabilities more efficiently.
From customer service and education to AI companionship and smart wearables, Zhao Bin believes conversational AI is entering more real-world scenarios. Whether AI can truly create value depends not only on whether the model "can speak," but also on whether it can understand needs, communicate naturally, and continuously complete tasks. Real-time engagement technology will play an increasingly important role in this process.
Afterward, Andrey Norkin, Chief Architect at NVIDIA and Co-Chair of the AOMedia Video Codec Working Group, gave a speech on AV2 video codec technology.
Roundtable Discussion: Will Personal Agents Become the Next-Generation Personal Entry Point?
In the first roundtable moderated by Agora co-founder Tony Wang, interactive media product manager and tech blogger Eugene Wei, tech self-media writer and host of the podcast "Luanshushu" Pan Lu, and AIoT hardware entrepreneur and host of the edge AI self-media channel Hua Jianxin discussed the topic "Personal Agents: From New Tools to New Entry Points?"
From phones, glasses, and earphones to more wearable devices, personal agents are reigniting industry reflection on the next-generation human-computer interaction entry point. Pan Lu believes that personal agents may bring a paradigm shift: the value of AI products is shifting from competing for user attention to helping users complete tasks more efficiently. Future personal agents should not only respond to explicit commands but also proactively take on tasks, helping users handle matters that have clear goals yet are not worth investing significant time in.
Regarding next-generation personal hardware, Hua Jianxin proposed that the future entry point may not be monopolized by any single device; glasses, earphones, and other hardware capable of sensing the environment and executing tasks all have opportunities. He believes that personal agents not only need to understand users but also need to continuously perceive the real world and take action through physical devices, which opens up new development space for hardware of different forms.
Eugene Wei steered the discussion toward the value of "context": whether a personal agent can truly understand a user's interests, communication records, and social relationships will determine whether it can become a valuable personal entry point. When measuring whether a new entry point is viable, he also suggested watching how users interact with the Agent each day, and whether users initiate contact with the Agent more often, or the Agent initiates contact with users more often. The roundtable went on to further discuss the product value of personal agents, hardware forms, and future metrics for evaluation.
Roundtable Discussion: From "Able to Chat" to "Able to Get Things Done" — How Can Conversational AI Create Real Value?
In the second roundtable moderated by Agora Chief Business Officer Cui Bo, Xieyue Intelligence founder Chen Wei, Guanke Technology founder Geng Xianglei, Rokid Leqi co-founder and head of ecosystem Cai Guoxiang, and Titan Qiming CEO Wu Kan started from different scenarios—embodied AI, smart wearables, enterprise marketing, and AI recruiting—to explore conversational AI: driving next-generation human-Agent interaction.
Chen Wei believes that the key to embodied AI is truly converting human intent into robot actions. Robots must not only understand voice commands but also integrate multimodal information such as vision, speech, and their own state to complete perception, planning, and decision-making about the physical environment, and continuously adjust task execution based on environmental changes after acting. Rather than completing pre-set demonstration tasks, what matters more for robots is continuously understanding people's real needs in open environments, keeping actions consistently aligned with human intent. Xieyue Intelligence is developing the Duplex Reasoning embodied foundation model, an entirely new paradigm aimed at achieving integration of robot interaction and action.
Cai Guoxiang, drawing on AI glasses practice, emphasized that conversational experience is the core competitiveness of AI wearable devices. He stated that no matter how powerful the hardware and the underlying AI capabilities are, if the conversation is not natural enough, the user experience will be directly affected. In the future, AI wearable devices need to achieve low-latency, stable real-time interaction, along with understanding of semantics and long-term context, so that users gradually stop feeling they are talking to an AI. He also shared the practice of the Rokid Leqi AI assistant using Agora RTC link services, and is optimistic that AI glasses will become an important personal entry point in the AI era.
In enterprise application scenarios, Geng Xianglei pointed out that for AI voice agents to deliver business reliably, they must solve problems such as latency, interruption timing, and human-like expressiveness, among which latency may even directly affect task outcomes. For To B marketing, AI also needs to be combined with industry knowledge systems and human collaboration to better safeguard business results. Wu Kan, drawing on AI recruiting practice, said that conversational AI can help recruiting businesses reach job seekers at scale and improve service efficiency, rather than simply replacing humans. To form a closed business loop, it is also necessary to accumulate industry data, organize the business around job seekers as the core entity, help Agents build long-term memory, and, centering on actual business events such as interviews and onboarding, assist AI in continuously evaluating and optimizing service quality.
From the sharing of the four guests, it can be seen that although different industries have varying requirements for conversational AI, they all point in one common direction: AI must not only be able to converse, but also understand real scenarios, integrate into existing business processes, and complete tasks reliably. As real-time interaction, multimodal perception, and Agent execution capabilities continue to develop, conversational AI is expected to evolve from an interaction tool into an important force connecting the digital and physical worlds and driving business operations.
From real-time interaction to real-time intelligence, opening the next chapter of conversational AGI
From the five-level conversational capability framework proposed by Zhao Bin, to the two roundtables discussing personal agents and real business implementation, the iRTE2026 main forum presented a clear industry trend: the competition in conversational AI is extending from foundational model capabilities to contextual understanding, real-time interaction, complex relationship cognition, and task execution.
When AI is no longer limited to passively answering questions, but can continuously understand people, actively participate in conversations, and complete tasks in real scenarios, real-time interaction technology will also take on a deeper mission.
Facing the next stage of conversational AGI, Agora will continue to explore the integration of real-time interaction and generative AI together with developers and industry partners, promoting more natural and efficient real-time interaction experiences between people and between people and Agents.
This is an original Leifeng Network article; unauthorized reproduction is prohibited. For details, seeReprint Notice。