Accepted for NeurIPS 2026 · Sydney

RTCA 2026

Real-Time Conversational Agents: Toward Natural Multimodal Interaction

RTCA looks to explore the challenges of realtime conversational agents across multiple modalities.

Call for papers Contact organizers

Date TBC Dec 11th or 12th 2026

Location Sydney, Australia

Format Full-day, in-person

Submission Deadline Aug. 29, 2026 AoE

Why RTCA

Real-time interaction is a different research problem.

Conversational AI has moved beyond text chat into voice modes, visual avatars, shared screens, and tools. Systems that feel natural must stream speech, video, and language while listening, watching, and re-planning continuously with challenging latency constraints.

RTCA focuses on the problems that offline generation can afford to ignore: latency, partial observability, turn-taking, backchannels, interruptions, cross-modal alignment, and evaluation of interactional naturalness.

Real-Time Generation

Streaming speech, video, and language under hard latency budgets.

Naturalness in Interaction

Prosody, gaze, timing, grounding, expressivity, and turn-taking dynamics.

Evaluation of Live Systems

Metrics and protocols for responsiveness, perceived latency, and conversational quality.

Scope

Topics of interest

We invite original contributions from speech, vision, language, HCI, social-signal processing, and ML systems communities working on interactive multimodal agents, including but not limited to:

Streaming/low-latency speech synthesis, ASR, and full-duplex audio–language models

Real-time talking-head, avatar, and embodied video generation; lip-sync, gaze, expressivity under streaming

Streaming language models; incremental and speculative decoding for dialogue

Turn-taking, backchanneling, interruption handling, and floor management

Multimodal alignment under latency and partial-observation constraints

Prosody, emotion, and paralinguistic generation in interactive settings

Memory, grounding, and tool use during live conversation

Evaluation of naturalness: perceptual studies, turn-taking metrics, perceived latency, interactive Turing-style tests

Datasets and benchmarks for interactive (not offline) evaluation

Efficient inference, on-device deployment, and the systems–quality trade-off

Safety, identity, and trust in real-time agents (deepfakes, persuasion, consent)

Invited Talks

Invited speakers

To be confirmed.

Workshop Day

Tentative schedule

RTCA is planned as a full-day in-person workshop with invited talks, contributed talks, posters, live demos, and a closing panel. Times and sessions below are tentative and subject to change.

08:45Welcome
09:00Invited talk: real-time speech and full-duplex audio LMs
09:40Invited talk: streaming video and avatar generation
10:20Coffee and poster setup
10:45Contributed talks I
11:25Invited talk
12:05Lunch
13:30Poster session with concurrent live-demo booths
14:30Invited talk
15:10Contributed talks II
15:50Coffee
16:15Conversational Agents Showcase: live interactions with deployed and research systems
17:00Panel: What does naturalness mean, and how should we measure it?
17:55Best paper and best demo announcements; close

Submissions

Call for papers

The call for papers opens July 18, 2026. Submissions (papers and demos) are due August 29, 2026 AoE via OpenReview (portal link to be published here), formatted for double-blind review using the NeurIPS 2026 style file.

Full papers

Up to 8 pages. Original contributions; may be presented as posters and/or contributed talks.

Short papers

Up to 4 pages. Work in progress or focused contributions.

Demo papers

Up to 2 pages.

Important dates

July 18: Call for papers opens
Aug. 29 AoE: Submission deadline (papers and demos)
Sep. 29 AoE: Author notification
Dec. 11 or 12: Workshop day, Sydney, Australia

Page limits exclude references and appendices. The workshop is non-archival; authors retain the right to publish elsewhere. Dataset submissions should include an ethics statement covering consent for voice or likeness, deepfake risk, and provenance. The workshop follows the NeurIPS Code of Ethics, Code of Conduct, and Main Track LLM policy. Questions? Contact us at rtca-workshop@googlegroups.com.

Team

Organizers

The organizing team spans industry and academia across real-time agents, digital humans, social robotics, affective computing, computer vision, and multimodal AI.