论文检索

Inge Vejsbjerg, Rahul Nair, Elizabeth M. Daly, Dhaval Salwala, Seshu Tirupathi

We present Risk Atlas Nexus, an open source system for governing AI risks. The system unifies several risk classification frameworks through a common ontology. Given an AI application use case (called an intent), the system estimates risks and associated mitigations that are linked to identified risks. The tool is designed to be incorporated in AI governance workflows where recommendations can be translated to business controls to cover risks arising from AI use in firms.

Purna Chandra Sekhar Vakudavathu, Kushal Mukherjee, Jayachandu Bandlamudi, Renuka Sindhgatta, Sameep Mehta

Although LLMs can generate tools for generic domains and tasks, they struggle with enterprise-related domains that involve proprietary APIs and data schemas. We present ToolSmith, a framework for autonomously generating and validating agent-compatible tools. Given an API specification and a Tool Specification Requirement (TSR), ToolSmith produces a tool function and verifies it through a closed-loop process: it creates natural language (NL) tests and executes the tool in a secure agent sandbox for validation. For state-changing tools, ToolSmith confirms outcomes by querying the API with parameters derived from the NL tests. If the tool fails to produce the desired output, ToolSmith generates diagnostic feedback to iteratively regenerate it. By ensuring both functional correctness and agent compatibility, ToolSmith enables reliable automation of enterprise workflows.

Bekir O. Turkkan, Pavankumar Murali, Chandrasekhar Narayanaswami, Vadim Sheinin

The dynamic nature of cloud spending and pricing structures pose challenges for practitioners in IT Financial Operations (FinOps). Recent advances in agentic systems enables them to instead rely on agents for complex FinOps tasks such as drawing insights from their data through natural language queries. In this work, we present an IT FinOps Data Insights Agent, that implements “chat with your data” approach to support practitioners in their daily tasks. Our agent achieves up to 90% accuracy across ITBench FinOps scenarios.

Yuyang Tian, Shunqiang Mao, Wenchang Gao, Lanlan Qiu, Tianxing He

Large Language Models (LLMs) have revolutionized the simulation of agent societies, enabling autonomous planning, memory formation, and social interactions. However, existing frameworks often overlook systematic evaluations for event organization and lack visualized integration with physically grounded environments, limiting agents' ability to navigate spaces and interact with items realistically. We develop MiniAgentPro, a visualization platform featuring an intuitive map editor for customizing environments and a simulation player with smooth animations. Based on this tool, we introduce a comprehensive test set comprising eight diverse event scenarios with basic and hard variants to assess agents' ability. Evaluations using GPT-4o demonstrate strong performance in basic settings but highlight coordination challenges in hard variants.

Yolo Yunlong Tang, Jing Bi, Chao Huang, Susan Liang, Daiki Shimada, Hang Hua, Yunzhong Xiao, Yizhi Song, Pinxin Liu, Mingqian Feng 等

In this work, we introduce CAT-V (Caption Anything in Video), a training-free framework for fine-grained object-centric video captioning of user-selected instances. CAT-V combines (i) a SAMURAI-based Segmenter for precise object masks across frames, (ii) a TRACE-Uni Temporal Analyzer for event boundary detection and coarse event descriptions, and (iii) an InternVL-2.5 Captioner that, conditioned on spatiotemporal visual prompts and chain-of-thought (CoT) guidance, produces detailed, temporally coherent captions about object attributes, actions, states, interactions, and context. The system supports point, box, and region prompts and maintains temporal sensitivity by tracking object states across segments. In contrast to vanilla video captioning that is overly abstract and dense video captioning that is often terse, CAT-V enables object-level specificity with spatial accuracy and temporal coherence, without additional training data.

Roman Sultimov, Mikhail Mozikov, Dmitrii Abramov, Mariia Kovalchuk, Maksim Malykh, Ilya Makarov, Andrei Osiptsov, Aleksandr Volkov, Yury Maximov

Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.

Jose Daniel Galvan Suazo, Hugo Albert Bonet, Carlos Monserrat-Aranda, Cèsar Ferri

The floods caused by the Isolated High-Level Depression (DANA) in the Valencian Community in October 2024 destroyed and damaged hundreds of thousands of personal photographs, erasing key pieces of collective and emotional memory. Within the project Recuperar las Memorias, we present an AI-based system for automated photo reconstruction, designed to support the recovery of more than 200,000 affected images. The system integrates YOLOv8 and SAM2 for automatic detection of damaged regions, followed by context-aware inpainting to restore visual coherence. Special modules are included for facial restoration, preserving identity in one of the most emotionally critical aspects of personal photographs. The tool is deployed as a web application that enables both single-image and batch restoration, making it accessible to non-expert users. Preliminary evaluation, combining human perceptual studies and automatic metrics (LPIPS), shows consistent alignment between subjective and objective assessments of quality. This demonstration highlights how advances in computer vision can be mobilised in real-world crisis contexts, placing AI at the service of cultural heritage, dignity, and memory preservation.

Du Su, Zhenxing Chen, Shilong Zhao, Yuanhao Liu, Fei Sun, Qi Cao, Huawei Shen

Auditing recommendation systems has attracted growing attention due to increasing concerns over filter bubbles, unfairness, and data misuse. A common approach is sock-puppet auditing, where autonomous agents interact with platforms to reveal risks. However, existing approaches rely on hard-coded agents, lacking adaptability to dynamic GUI layouts and generating behaviors far from those of real users, limiting the comprehensiveness and representativeness of assessment. To address these issues, we introduce AuditAgent, an LLM-powered GUI-agent framework for risk auditing. AuditAgent simulates realistic user preferences and performs adaptive, human-like interactions on recommendation platforms. This design enables more thorough and faithful auditing, providing comprehensive assessments across multiple risk dimensions, including filter bubbles, unfairness, and data misuse.

Chathurangi Shyalika, Utkarshani Jaimini, Cory Henson, Amit Sheth

Modern manufacturing systems demand real-time, trustworthy, and interpretable insights into anomalies and their underlying causes. However, conventional pipelines treat anomaly detection, causal inference, and decision-making as siloed tasks, lacking integration, explainability, and adaptability. We present CausalPulse, an intelligent, multi-agent copilot for automated Root Cause Analysis (RCA) in industrial settings. Built on a modular and extensible architecture, the system leverages standard agentic protocols, including Model Context Protocol (MCP), Agent2Agent (A2A), and LangGraph for dynamic tool and agent discovery and seamless orchestration of tasks. Agents dynamically interact to perform data preprocessing, anomaly detection, causal discovery, and root cause analysis through a neurosymbolic workflow that combines symbolic reasoning with neural methods. Intelligent postprocessing pipelines enable automatic chaining of agent tasks, enhancing contextual awareness and adaptability. CausalPulse is evaluated using both an academic public dataset (i.e., Future Factories) and an industrial proprietary dataset (i.e., Planar Oxygen Sensor Element) and shows that the system outperforms traditional baselines in interpretability, trustworthiness, and operational utility.

Enrico Scala, Francesco Percassi, Mauro Vallati

The expressive power of PDDL+ is crucial in a wide range of real-world applications, where it is necessary to represent hybrid discrete-continuous changes and environmental dynamics. Given the complexity of the dynamics that can be modelled in PDDL+ and the scale of the problems involved, the ability to validate plans and simulate their trajectories is essential for assessing the accuracy of the models. In this paper, we present PPS (PDDL Plus Simulator), a Java-based tool that enables seamless validation and simulation of PDDL+ plans under time-discrete semantics.

Ilias Sarbout, Mehdi Ounissi, Théo Cazenave-Coupet, Dan Milea, Daniel Racoceanu

We present City Of Light, a Unity-based, city-scale 116 km² simulator of Paris for high-throughput embodied AI research. COL fuses open geographic information system sources into geo-anchored, per-tile meshes and provides a configurable, stochastic runtime with controllable traffic and pedestrians. Agents receive frame-synchronized multi-sensor observations (RGB, depth, normals, semantics) and execute step-synchronized actions to navigate the environment. To support high-rate vision pipelines, we introduce TURBO, a Unity-Python bridge that streams multi-camera observations and allows control at up to 1300 FPS, achieving higher throughput than ML-Agents in our benchmark. We also provide a Street View Digital Twin that aligns simulator viewpoints with corresponding real-world panoramas for frame-accurate visual comparison and quantitative matching. COL enables fast scripting, large-scale data collection, and reinforcement learning in geo-anchored urban settings.

Mark David Rice, Gu Ying, Kelvin Wei Lim, Qing Yu Hoo, Liyuan Li, Lee Jue Ying, Jacky Jie Wei Tan, Lai Xing Ng, Jamie Ng

In this paper, we present the development of an automated visual inspection system designed to detect defects on the upper surface of an aircraft airframe. Specifically, the system employs a multi-camera PTZ (Pan-Tilt-Zoom) set-up to capture and process images from designated regions. Custom developed software manages path planning and camera localization, while a hybrid-AI framework is integrated to identify various defect types, including missing and damaged components. The demonstration highlights the system’s detection capabilities and prototype functionalities using a large aircraft model, supported by a user interface to monitor progress and visualize results. To help validate this work, performance evaluations were conducted using selected multimodal and object detection models.

Christopher B. Rauch, Rosina O. Weber

Professional ethics committees currently lack structured tools to identify relevant ethical concepts from complex narratives and compare them against prior decisions. ProEthica analyzes professional ethical scenarios against established codes and precedent cases. The system uses large language models (LLMs), leveraging their natural language processing capabilities to extract nine types of components (Roles, Principles, Obligations, States, Resources, Actions, Events, Capabilities, and Constraints) from case text and scenario descriptions. Domain-specific ontologies provide precise definitions that constrain LLM output to match formal concept specifications, ensuring consistency across extraction and validation. Case-based reasoning identifies precedent cases and analogous situations relevant to the scenario under analysis. The current implementation processes engineering ethics cases with complete provenance tracking and ontology-driven validation. The framework supports extension to other professional domains with established codes and precedent systems.

Balaji Rao, Naveen Mathews Renji, Elena Korshakova, Carlo Lipizzi

Steve is an AI career coaching platform that turns a resume and insights from an AI-enabled chat with a user into a personalized skill gap report and upskilling roadmap. The platform suggests a personalized course plan, supports continuous learning, and helps shape the user’s career trajectory. Steve is built around schema-constrained JSON artifacts and a configurable career-tree ontology. The system compares confirmed skills against role-specific requirements, prioritizes gaps (critical/important/beneficial), and translates the analysis into embedding-based queries over the course index. Steve has three personas (Interview Coach, Resume Evaluator, and Career Coach) that provide concise feedback tailored to the user’s goals and context. Steve also supports speech Input/Output (I/O) via Whisper-based speech-to-text and a dual-voice text-to-speech layer, enabling users to talk to Steve. The platform offers flexible adaptability across institutions, enabling them to configure deployments by substituting their own ontologies and course catalogs. Our demo uses STEM trajectories as a case study, but the pipeline is domain-agnostic by design. Users can edit inputs, check speech recognition accuracy, and observe consistent updates, illustrating a reproducible, human-in-the-loop pattern for deploying LLMs in career guidance. Steve is currently in its alpha stage and available for demonstration.

Sampath Rajapaksha, Nirmalie Wiratunga, Ikechukwu Nkisi-Orji, Tim Clarke, Fraser Kerr

Capturing expertise and enabling efficient information retrieval are critical in the energy sector, where high staff turnover can lead to significant knowledge loss. Retrieval Augmented Generation (RAG) offers a solution by grounding Large Language Model (LLM) outputs in documented sources, but its effectiveness is limited by reliance on general-purpose embeddings. We present Wikatoni, an agentic AI system for energy engineering workflows that integrates a novel domain-specific embedding model. Wikatoni combines fine-tuned embeddings with agentic RAG, metadata filtering, and hybrid retrieval to improve document search, automated reporting, and workflow efficiency. Evaluation on internal enterprise offshore energy data shows that the domain-adapted embedding improves recall by 10%, and Wikatoni agentic RAG further increases answer accuracy by 14% compared to vanilla RAG with the base embedding model, achieving the best overall performance in context recall, faithfulness, and answer accuracy.

Hangwei Qian, Yang He, Yaxin Shi, Ivor Tsang

In this demo, we present GenMatLab, a user-friendly web platform that makes latest AI techniques accessible for inverse materials design. The platform integrates data analysis and generative modeling into an easy-to-use interface, enabling researchers, material domain experts, and practitioners to explore and apply AI techniques without requiring advanced coding expertise. At its core are generative AI models that support interactive operations, allowing users to conduct inverse design and investigate generated candidates in an intuitive and exploratory way. By lowering technical barriers, GenMatLab empowers a broader community to leverage cutting-edge AI methods for accelerating materials discovery.

Suraj Prasai, Mengnan Du, Ying Zhang, Fan Yang

We develop KnowThyself, an agentic assistant that advances large language model (LLM) interpretability. Existing tools provide useful insights but remain fragmented and code-intensive. KnowThyself consolidates these capabilities into a chat-based interface, where users can upload models, pose natural language questions, and obtain interactive visualizations with guided explanations. At its core, an orchestrator LLM first reformulates user queries, an agent router further directs them to specialized modules, and the outputs are finally contextualized into coherent explanations. This design lowers technical barriers and provides an extensible platform for LLM inspection. By embedding the whole process into a conversational workflow, KnowThyself offers a robust foundation for accessible LLM interpretability.

Dhaval Patel, Nianjun Zhou, Shuxin Lin, James Rayfield, Chathurangi Shyalika, Suryanarayana Reddy Yarrabothula

Industrial automation increasingly relies on multi-agent AI, yet evaluation remains difficult due to task complexity and data confidentiality. We present AssetOpsBench-Live, a demo of a competition-ready platform for real-time, privacy-preserving evaluation of multi-agent AI in industrial contexts. The platform integrates AssetOpsBench, which measures six dimensions of multi-agent performance and performs automated failure-mode discovery, with Codabench, which supports reproducible, code-oriented competitions. End users first validate agents locally, then submit containerized code for execution on hidden industrial scenarios. Instead of raw trajectories, the system provides quantitative scores and clustered failure modes (e.g., reasoning--action mismatch, step repetition), enabling participants to identify failures, apply targeted improvements, and iteratively resubmit. By combining competition-based engagement with actionable diagnostics, AssetOpsBench-Live delivers reproducible, real-time insights reflecting real-world industrial constraints.

Sehyuk Park, Caren Han, Hyunsuk Chung

Time-series forecasting plays an essential role in domains such as finance, healthcare, and energy. Yet most existing systems operate in a unimodal setting, overlooking complementary information available from visual and textual modalities. There are surprisingly few time-series forecasting demos, and multimodal, interpretable demos are rarer still. In practice, it is difficult for users to experiment with foundation models on their own time-series data due to strict input requirements, heavy setup burdens, and limited interpretability support. We present MulTiCast, an interactive Multimodal Time series foreCasting system that enables users to combine numerical signals with visual and textual context to improve predictions. The system builds on pretrained models with lightweight adaptation, but its central contribution lies in the interactive demonstration platform. Through a web interface via Hugging Face Spaces, users can load datasets, toggle modality inclusion, and visualize forecasts together with the attention maps of each modality, providing insights into the reasoning path behind the predictions.

Heesoo Park, Sujin Park, Dongjun Lee

We present a practical system that supports in-depth analysis of cryptocurrency markets through timeline-based event detection and contextual summarization. Our framework processes continuous news streams, identifies price-relevant events, and organizes them into semantic timelines with concise background summaries generated by large language models (LLMs). This design allows traders and analysts to retrospectively explore events alongside price charts, facilitating a deeper understanding of how news developments relate to market fluctuations. By transforming unstructured news data into structured insights, the system provides a valuable tool for market analysis, risk evaluation, and behavioral studies in volatile trading environments.