论文检索

Sebastian Zimmermann, René Groh, Andreas M. Kist

Deploying AI on microcontrollers (MCUs) is challenging. We introduce MIMaaS, a Microcontroller-as-a-Service platform that enables users to upload a model, select a target device, and receive a detailed performance report remotely. A key innovation is our measurement of real-world power consumption, alongside latency and memory usage, directly from the physical hardware. MIMaaS empowers researchers and developers to easily create and validate hardware-aware AI models without needing physical hardware access.

Tammy Zhong, Yang Song, Maurice Pagnucco

Ethical awareness is critical for robots operating in human environments, yet existing automated planning tools provide little support. Manually specifying ethical rules is labour-intensive and highly context-specific. We present Principles2Plan, an interactive research prototype demonstrating how a human and a Large Language Model (LLM) can collaborate to produce context-sensitive ethical rules and guide automated planning. A domain expert provides the planning domain, problem details, and relevant high-level principles such as beneficence and privacy. The system generates operationalisable ethical rules consistent with these principles, which the user can review, prioritise, and supply to a planner to produce ethically-informed plans. To our knowledge, no prior system supports users in generating principle-grounded rules for classical planning contexts. Principles2Plan showcases the potential of human-LLM collaboration for making ethical automated planning more practical and feasible.

Yiran Zhang, Mingyang Lin, Mark Dras, Usman Naseem

Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VISTA, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VISTA allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model's step-by-step logical path. By providing a unified and interactive framework, VISTA significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models.

Junhao Zhang, Ming Kong, Zhanbin Hu, Hao Qin, Zhijie Xu, Xiaojun Zhu, Qiang Zhu

In this work, we propose a diffusion-based method for 3D-aware image composition. Previous approaches have focused on 2D-view image composition, which limits their handling of complex 3D spatial relationships. Consequently, they are not well-suited for applications requiring precise 3D object control and iterative refinement, including interior design visualization, visual effects prototyping, and virtual reality scene construction. In contrast, our method extracts 3D bounding boxes for all objects in the scene image. Users can then specify a new 3D bounding box based on existing spatial context and provide an image of the target object. Leveraging a fine-tuned diffusion model, our approach enables high-fidelity image composition while preserving the underlying 3D structure of the scene.

Hui Zhang, Guangchen Ruan, Hui Xiao

We present Magnol.AI Copilot, an extension of the Magnol.AI digital biomarker platform that integrates multimodal large language models (LLMs) to transform digital health technology (DHT) trial dashboards into conversational systems. Copilot augments the platform with a multi-agent orchestration layer and vision-enabled LLMs that interpret visualizations, tabular summaries, and textual metadata. The system enables natural language queries and automatic generation of contextual insights, allowing researchers to interact with wearable data through dialogue rather than static inspection. A case study with an actigraphy device demonstrates Copilot’s ability to identify nightly compliance gaps and provide contextual explanations, reducing cognitive load compared to manual dashboard review. This work presents a novel integration of IoMT infrastructure with multimodal LLMs, advancing digital biomarker research toward conversational and accessible DHT trial platforms.

Asaf Yehudai, Lilach Eden, Yotam Perlitz, Roy Bar-Haim, Michal Shmueli-Scheuer

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential for benchmarking, these top-level scores obscure the specific, actionable reasons behind a model's performance. To bridge this gap, we introduce CLEAR, an interactive, open-source package for LLM-based error analysis. CLEAR first generates per-instance textual feedback, then it creates a set of system-level error issues, and quantifies the prevalence of each identified issue. Our package also provides users with an interactive dashboard that allows for a comprehensive error analysis through aggregate visualizations, applies interactive filters to isolate specific issues or score ranges, and drills down to the individual instances that exemplify a particular behavioral pattern. We demonstrate CLEAR analysis for RAG and Math benchmarks, and showcase its utility through a user case study.

Jinseok Yang, Jung-Hee Kim, Juhyun Lyu, Soonyoung Lee, Woohyung Lim

Causal agents have emerged as promising tools for automating causal analysis based on user queries. However, existing causal agent systems are often limited to a single causal task, limiting their ability to handle complex queries. In addition, they accept only numerical data as input, preventing the integration of domain knowledge expressed in natural language. To overcome these limitations, we propose the OrcheCause agent, a causal agent leveraging textual knowledge for end-to-end causal inference. Specifically, OrcheCause is designed to orchestrate a sequence of interrelated causal tasks in response to user queries. Furthermore, OrcheCause supports diverse data types—numerical as well as textual data—by extracting cause-effect pairs from the relevant sources and incorporating them into causal discovery (CD), thereby improving the performance of CD. OrcheCause also introduces a metric-based hyperparameter optimization framework for CD when ground-truth graphs are not available.

Jared Chan Xu Yang, Haokai Ma, Yunshan Ma

Developing new portfolio-management algorithms typically demands substantial programming effort, limiting rapid experimentation and excluding finance professionals without coding skills. Current robo-advisory tools offer pre-built but rigid strategies, restricting customization and experimentation. We introduce PortfolioPilot, an open-source, agentic platform that enables users to generate bespoke portfolio through natural-language descriptions. Leveraging the Anthropic Claude API, PortfolioPilot dynamically synthesizes executable TypeScript algorithms that run in the frontend with security validation. The system integrates real-time backtesting with historical market data, classical optimization algorithms (Markowitz, LSTM, ARIMA), and interactive performance visualizations.

Zhikai Xue, Tianqianjin Lin, Pengwei Yan, Ruichun Wang, Yuxin Liu, Zhuoren Jiang, Xiaozhong Liu

Chronic diseases have become the leading cause of death worldwide, a challenge intensified by strained medical resources and an aging population. Individually, patients often struggle to interpret early signs of deterioration or maintain adherence to care plans. In this paper, we introduce VitalDiagnosis, an LLM-driven ecosystem designed to shift chronic disease management from passive monitoring to proactive, interactive engagement. By integrating continuous data from wearable devices with the reasoning capabilities of LLMs, the system addresses both acute health anomalies and routine adherence. It analyzes triggers through context-aware inquiries, produces provisional insights within a collaborative patient–clinician workflow, and offers personalized guidance. This approach aims to promote a more proactive and cooperative care paradigm, with the potential to enhance patient self-management and reduce avoidable clinical workload.

Zekun Xi, Ziyan Jiang, Yujie Bao, Zhenqian Xu, Shumin Deng

Despite the rapid advancement of generative agents, their deployment in real world industry scenarios often encounters challenges due to a lack of domain-specific knowledge. To address this gap, we present KnowPilot: a Domain-Specific Knowledge Augmented Agent System. KnowPilot is an open-source framework that integrates task-specific priors, explicit knowledge, and experiential knowledge to enhance agent performance in specialized applications. It combines knowledge retrieval from structured repositories with a memory system capable of capturing expert experience through human–AI interaction.

Zekun Wu, Seonglae Cho, Cristian Enrique Munoz Villalobos, Theo King, Umar Mohammed, Emre Kazim, Maria Perez-Ortiz, Sahan Bulathwela, Adriano Koshiyama

Modern Agentic AI systems plan, reason, and act across multiple steps, creating execution patterns that are difficult to interpret. Existing observability platforms track prompt I/O and operational metrics but require manual inspection of traces to reconstruct structure and reasoning. We present AgentGraph, which converts execution logs into interactive knowledge graphs and actionable insights. Nodes represent agents, tasks, tools, data inputs/outputs, and humans, while typed edges capture relations such as inputs consumed, tasks delegated or sequenced, tools required or used, outputs produced and delivered, and interventions from agents or humans. Each graph element links to its exact trace span, ensuring verifiability. Building on this representation, AgentGraph enables two analyses: qualitative trace-grounded failure detection and optimisation recommendations, and quantitative robustness evaluation via perturbation testing and causal attribution.

Ilham Wicaksono, Zekun Wu, Rahul Patel, Theo King, Adriano Koshiyama, Philip Colin Treleaven

We present AgentSeer, an interactive observability framework for agentic AI systems. Unlike conventional tracing tools that expose raw spans or model-centric metrics, AgentSeer introduces a dual graph decomposition constructed through a deterministic rule-based parser: a temporal action graph, where each prompt or tool invocation is represented as a distinct action, and a component graph capturing architectural relations among agents, tools, and memory modules. Beyond visualization, AgentSeer enables action-level red teaming, where jailbreak payloads are systematically attached to every action node (including agent messages, tool calls, and memory retrievals) to uncover vulnerabilities invisible to model-level testing. Our demonstration features a six-agent hierarchical testbed with interactive visualization and deployment-oriented safety evaluation applied directly on the same prompts and contexts, systematically revealing high-risk interactions, context-dependent vulnerabilities, and emergent behaviors. By combining structured decomposition, automated red teaming, and rule-based reliability, AgentSeer establishes a safety-first methodology for observability in multi-agent AI.

Daniel Karl I. Weidele, Priyanshu Rai, Frederico Araujo, Teryl Taylor, Radu Marinescu

We present AutoTuneX, a system architecture design and implementation for users to interactively fine-tune large language models (LLMs) based on automated hyperparameter optimization particularly built around Bandit Limited Discrepancy Search. Next to a classical Graphical User Interface (GUI) our system features an agentic runtime to facilitate automated fine-tuning via chat.

Zhuoran Wang, Dylan Raharja, Yujia Hu, Roy Ka-Wei Lee

We present SafeLens, a lightweight segment-level video moderation system that fuses speech, text, and visual frames to produce hateful content detection for each segment. For every segment, SafeLens returns a structured prediction: label, prediction confidence, reasons for flag, harm categories. The structured predictions are optimized for triage, appeals, and downstream enforcement. The system is modular (pluggable speech, text, and visual processing modules back-ends and a mid-size policy Language Language Model (LLM) agent with parameter-efficient tuning). In the live demo, attendees can upload or select clips, scrub the timeline to flag hateful segments, inspect rationales, and vary the policy LLM agent to benchmark the hateful content moderation performance.

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.