Demonstration Program

The AAAI-26 Demonstrations Program is intended to foster discussion and exchange of ideas among researchers and practitioners from academia and industry by presenting software and hardware systems and research prototypes of such systems, including their capabilities and workings. All accepted demos will be allocated time for live demonstrations. Accepted demonstrations will also have a short paper included in the proceedings.

Note that AAAI-26 is planned an in-person conference, thus at least one author of every accepted demo will be expected to present the work in person.

Demonstrations will be held during the poster sessions. The list of demos scheduled on each day is available below.

Demo presenters: each demo will be provided with the following resources:

• (1) approx. 6’ x 30”H draped table
• (1) monitor on stand
• (1) shared poster board (2m wide by 1.2m high) A0 size with portrait orientation recommended
• (1) 13 amp / 220V socket

Program Overview

3D4D: An Interactive, Editable, 4D World Model via 3D Video Generation
A Visualized Framework for Event Cooperation with Generative Agents
AEGIS: Toward Expert-in-the-loop Industrial Anomaly Detection
AgentGraph: Trace-to-Graph Platform for Interactive Analysis and Robustness Testing in Agentic AI Systems
Agentic Solutions for IT Financial Operations
AgentSeer: Visualizing and Evaluating Temporal Actions in Agentic AI Systems
AI for Memory Preservation: Automated Restoration of Photographs Damaged by Floods
AirNavigation: Let UAV Navigation Tell Its Own Story
ARGUS: Towards End-to-End Argument Mining with Large Language Models
AssetOpsBench-Live: Privacy-Aware Online Evaluation of Multi-Agent Performance in Industrial Operations
AuditAgent: LLM Agent for Risks Auditing in Recommender Systems
Auto-BenchmarkCard: Automated Synthesis of Benchmark Documentation
Automated Multi-Camera Inspection System for Aircraft
AutoTuneX: Interactive Automated Fine-Tuning for Large Language Models
Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA
Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting
CausalPulse: Agentic Copilot for Root Cause Analysis in Smart Manufacturing
Chatsparent: An Interactive System for Detecting and Mitigating Cognitive Fatigue in LLMs
City of Light (COL): A City-Scale, Geo-Anchored Urban Simulator with High-Throughput Multi-Sensor Streams
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
DFAgent: From Natural Language Data Interactions to Reusable Agent-Ready Tools
Docora: A System for Interactive Knowledge Extraction and Visualization from Scientific PDFs
DS SERVE: A Framework for Efficient and Scalable Neural Retrieval
DTECT: Dynamic Topic Explorer & Context Tracker
Elevating AI on the Edge: A Demonstration of MIMaaS (Machine Intelligence with Microcontroller-as-a-Service)
Evaluating the Factuality of Large Language Models Using Multiple Plug-and-Play Fact Sources
Federated Learning Playground
Framework GNN-AID: Graph Neural Network Analysis, Interpretation and Defense
GAICo: Demonstrating a Unified Framework for Multi-Modal GenAI Evaluation
GenMatLab: A Generative Platform for Inverse Materials Design
GeoProblem Factory: A Visual Interaction System for Solvable and Controllable Geometric Problem Generation by Leveraging Symbolic Deduction Engine
GPTKB v1.5: A Massive Knowledge Base for Exploring Factual LLM Knowledge
In-Situ Eval: A Modular Framework for Custom and Real-Time RAG Benchmarking
IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection
InTimeAD: Interactive Time Series Anomaly Detection
KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks
KnowThyself: An Agentic Assistant for LLM Interpretability
Magnol.AI Copilot: Multimodal LLMs for Conversational Insight Generation
Market-Aware Event Timeline Summarization: Integrating Price Signals to Improve Financial News Understanding
MemoVision: A Digital Catalog for Everyday Interactions
MulTiCast: A Multimodal Time Series Forecasting System
Next-Generation Metalens Vision System: Powered by AI and Applied to AI
OMEGA: An Ontology-Driven Tool for Explaining Multi-Agent Path Finding
OrcheCause Agent: From Textual Knowledge to End-to-End Causal Inference
PAGER: Proactive Monitoring Agent for Enterprise AI Assistant
PAL: Personal Adaptive Learner
PANSim: Visualization Tool for Planning and Acting against Nature
PHOTONS: Pose-Free Human-Centric Photo-Realistic Real-Time Novel View Synthesis from Sparse Views
Placing Any Object at Any 3D Position
PortfolioPilot: An Agentic Platform for Financial Portfolio Management Algorithm Development and Evaluation
PPS: An Efficient Java-based Simulator for Time-Discrete PDDL+
Principles2Plan: LLM-Guided System for Operationalising Ethical Principles into Plans
ProEthica: A Professional Role Based Ethical Analysis Tool Using LLM-Orchestrated, Ontology Supported Case Based Reasoning
QueryGym: Step-by-Step Interaction with Relational Databases
RAPID: A Rapid Prototyping Platform for Industrial Automation
RefLens: End-to-End Evidence-Grounded Citation Verification with LLM Agents
RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents
Risk Atlas Nexus: A System for Managing AI Risks
Risk-Aware Bilingual Spoken Dialogue for Campus Mental Health Support
RL-Studio: A System for Multi-Phase Reinforcement Learning Experimentation
SafeLens: Segment-Level Hate Speech Detection in Online Videos
SHARE: Synthesizing Heterogeneous Autism-support Records into Evidence-based Recommendations
SmartEyes: Plug-and-Play Event Detection for Retail Loss Prevention
Steve: Your Personal AI Career Coach
ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation
TPR: A Training Procedure Representation to Augment XR Simulations with LLMs
Traffic Signal Plans Explorer: A General Framework for Visualising Traffic Evolution
VitalDiagnosis: AI-Driven Ecosystem for 24/7 Vital Monitoring and Chronic Disease Management
VulnBench: A Comprehensive Benchmark for Transformer-Based Vulnerability Detection
Wikatoni: An Agentic AI System for Energy Engineering Workflows
Wikontic: A Tool for Building Knowledge Graphs from Text Aligned with the Wikidata Ontology

For More Information

Inquiries concerning demonstration submissions and suggestions may be directed to the demonstration program cochairs at aaai26dpchairs@aaai.org. All other inquiries should be directed to AAAI at aaai26@aaai.org.

Demonstration Program Cochairs

Shirin Sohrabi (IBM Research, USA)

Sarath Sreedharan (Colorado State University, USA)