论文检索

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.

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.

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.

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.

Bharath Muppasani, Ritirupa Dey, Biplav Srivastava, Vignesh Narayanan

Multi-Agent Path Finding (MAPF) algorithms provide highly optimized solutions for coordinating multiple agents in shared environments, yet their outputs lack explainability to human stakeholders. Existing explanation approaches, such as visual trace segmentation or logic-based reasoning, remain fragmented. In this demo, we present OMEGA, an interactive explanation platform that generates Natural Language (NL) explanations using the novel Multi-Agent Planning Ontology (maPO). Our framework transforms raw MAPF planner execution logs into a semantic knowledge graph, enabling SPARQL-based explanations of collision events, replanning strategies, and efficiency trade-offs. A lightweight web interface allows users to query, visualize, and interpret planner decisions, thereby making MAPF solutions transparent and auditable. We conducted a user study that confirms the ontology-driven explanations are significantly clearer and more preferred than raw logs, underscoring the potential of semantic technologies for explainable multi-agent systems.

Kirill Lukianov, Mikhail Drobyshevskiy, Georgii Sazonov, Mikhail Soloviov, Ilya Makarov

The rising demand for Trusted AI (TAI) underscores the need for interpretable and robust models, yet existing tools rarely support graph-structured data or integrate interpretability with security. At the same time, Graph Neural Networks (GNNs) deliver state-of-the-art performance on numerous graph tasks. We present GNN-AID (Graph Neural Network Analysis, Interpretation, and Defense), an open-source Python framework for analyzing, interpreting, and defending GNNs, addressing this critical gap. Built on PyTorch-Geometric, GNN-AID offers preloaded datasets, model libraries, flexible APIs, and a web interface for visualization and no-code model design. MLOps features further support reproducibility and experiment tracking.

Aris Hofmann, Inge Vejsbjerg, Dhaval Salwala, Elizabeth M. Daly

We present Auto-BenchmarkCard, a workflow for generating validated descriptions of AI benchmarks. Benchmark documentation is often incomplete or inconsistent, making it difficult to interpret and compare benchmarks across tasks or domains. Auto-BenchmarkCard addresses this gap by combining multi-agent data extraction from heterogeneous sources (e.g., Hugging Face, Unitxt, academic papers) with LLM-driven synthesis. A validation phase evaluates factual accuracy through atomic entailment scoring using the FactReasoner tool. This workflow has the potential to promote transparency, comparability, and reusability in AI benchmark reporting, enabling researchers and practitioners to better navigate and evaluate benchmark choices.

Fen Fang, Muli Yang, Henan Wang, Xinan Liang, Tobias Mass, Xuewu Xu, Xulei Yang, Zhengguo Li

Metalenses have been widely recognized as a key building block of next-generation optical systems, offering unprecedented advantages in compactness, lightweight design, and scalable manufacturing compared to traditional refractive optics. Despite this promise, practical use is limited by optical aberrations, blur, and illumination sensitivity, which degrade both visual quality and machine perception. In this demonstration, we present an end-to-end metalens vision system—from hardware sensing with a custom-built RGB metalens camera, to physics-informed imaging and real-time restoration, and finally to downstream vision applications such as object detection and depth estimation. By integrating spatially-aware attention enhancement and reinforcement learning-based illumination control into a real-time system, our solution transforms degraded raw captures into high-fidelity images that are both visually interpretable and functionally reliable for machine vision. This AI-powered pipeline highlights metalenses as a cornerstone for next-generation imaging, where advances in optics and machine intelligence jointly drive the future of visual perception.

Alla Chepurova, Aydar Bulatov, Mikhail Burtsev, Yuri Kuratov

Knowledge Graphs (KGs) provide structured, verifiable representations that ground facts and supply large language models (LLMs) with reliable real-world information. Building high-quality KGs from open-domain text remains difficult due to redundancy, inconsistency, and lack of ontology grounding. We present Wikontic, a pipeline that extracts triples from text with LLMs and refines them through ontology-based typing, schema validation, and entity deduplication, yielding compact and coherent graphs. Unlike prior frameworks that lack ontology grounding or perform only partial deduplication, Wikontic uniquely integrates entity canonicalization, alias tracking, and automatic enforcement of Wikidata’s ontology, enabling robust schema-aware construction without manual schema design. Its web interface lets users upload text, visualize graphs, and perform multi-hop question answering. By combining LLM flexibility with Wikidata’s ontological rigor, Wikontic transforms ambiguous text into structured, interpretable, and actionable knowledge.

Saumya Chauhan, Mila Hong

Supporting children with Autism Spectrum Disorder (ASD) requires highly individualized knowledge. However, critical information is often dispersed across documents such as Individualized Education Plans (IEPs), diagnostic assessments, and caregiver notes. Thus, we propose SHARE (Synthesizing Heterogeneous Autism-support Records into Evidence-based Recommendations), a framework that combines diverse autism-related documents into a concise, actionable set of recommendations for caregivers of children with ASD. Feedback is generated using OpenAI’s large language model API, grounded in user-provided evidence with optional web-based extensions for missing details, and citation-linked. After caregivers attempt and then rate recommendations, SHARE uses a Bayesian bandit algorithm with Upper Confidence Bound (UCB) re-ranking to refine future advice. While previous work mostly focuses on drafting static goals, SHARE additionally combines LLM-generated recommendations, caregiver feedback, and interpretable ranking into a pipeline that can adapt over time.

Suman Adhya, Debarshi Kumar Sanyal

To address the challenge of interpreting evolving themes in temporal text, we present DTECT (Dynamic Topic Explorer & Context Tracker), an interactive, end-to-end system for uncovering thematic dynamics. The system integrates a complete pipeline that supports data preprocessing, multiple model architectures, and dedicated metrics to analyze temporal topic quality. To enhance interpretability, DTECT features LLM-driven automatic topic labeling, trend analysis, interactive visualizations with document summarization, and a natural language chat interface. This cohesive platform empowers users to intuitively explore how topics change over time.

Hua Xu

While deep learning excels at decoding neural signals, the opacity of state-of-the-art models limits their scientific utility and clinical trustworthiness. We propose a research that bridges this gap by integrating high-performance architectures—specifically Transformers and Graph Neural Networks—with mechanistic interpretability and neuro-symbolic reasoning. This proposal aims to uncover verifiable mappings between artificial computational circuits and biological dynamics without compromising decoding accuracy. Validated through rigorous benchmarking and wet-lab experiments, this work establishes a foundation for transparent brain-computer interfaces and accelerates fundamental neuroscience research.

Srivarshinee S

This proposal aims to investigate epistemic uncertainty - uncertainty about knowledge or truth, often conveyed by modals like might or probably in Large Language Models (LLMs). By probing how such cues affect reasoning, we seek to achieve controllable epistemic sensitivity: enabling mod- els to interpret and adapt to uncertainty. Using activation- level analyses and multilingual benchmarks, this work ad- vances transparent, context-aware, and trustworthy reasoning in uncertainty-critical domains.

Yimeng Liu

RNA 3D structure prediction is essential for understanding regulatory mechanisms, catalysis, and therapeutic RNA design, yet progress has lagged behind proteins due to limited structural data and the complexity of RNA folding. This work proposes a data-efficient, physics-informed deep learning framework for full atomistic prediction of transfer RNA (tRNA) tertiary structures directly from sequence. Our approach will integrate pretrained RNA embeddings, predicted secondary structure constraints, and SE(3)-equivariant graph attention to model long-range geometric relationships. A two-stage design will first predict global phosphate backbone coordinates, then reconstruct nucleobase atoms using a local geometry-aware decoder. A multi-objective loss will combine geometric accuracy with chemical and biophysical plausibility to enforce valid torsion angles, base-pairing, and steric constraints. We will benchmark against physics-based (VFold) and neural network–based (DeepFoldRNA) models to assess generalization under data scarcity. Ultimately, this framework aims to advance RNA 3D modeling with improved stability, interpretability, and capacity to generalize beyond well-characterized RNA families, supporting future applications in rational RNA engineering and structure-guided RNA design.

Napassorn Litchiowong

I present a compact, testable architecture that endows learning agents with continuous proto-emotional dynamics and interpretable modulators (Persona, Ego, Shadow, Self). The design grounds these modulators in a computational interpretation of Jung’s Map of the Soul, mapping each archetype to a differentiable control that modulates policy selection via a bounded, low-dimensional affect vector. I describe concrete modular implementations, a staged experimental program (toy domains → multi-agent/social tasks → nonstationary transfer), baselines, ablations, and reproducible evaluation metrics.

Samruddhi Kamble

Sexual trauma leaves wounds that science cannot see, yet survivors live with them every day. Traditional tools rely on words or self-reports, often forcing survivors to "bleed in silence" when their pain is doubted or dismissed. Trauma, however, is not one-dimensional. It disrupts multiple brain networks and produces states fear, vigilance, detachment that cannot be captured by words alone. This creates the need for approaches that reveal trauma's complexity in ways that are both objective and interpretable. Our framework that combines fMRI, EEG, and DINO to investigate machine learning models can identify neural or psychological patterns associated with trauma responses. Instead of producing abstract scans or opaque predictions, the system will generate exploratory measures of trauma response that support therapists' understanding while guiding future research. These measures will be presented through a simple dashboard that summarizes three indices (TPI, DI, RBS) alongside heatmaps and plain language notes. By turning complex data into clear, anonymized session snapshots, the dashboard provides researchers with an output that can be compared across participants and refined in future work.

Zhiqing Cui

Spatiotemporal forecasting has seen remarkable progress with the advent of deep learning, particularly with Spatiotemporal Graph Neural Networks (STGNNs). These models excel at answering the what question: predicting future numerical values with high accuracy. However, they fail to answer the crucial why question. In high-stakes domains such as meteorology, urban planning, and public health, this opacity creates a critical bottleneck for adoption. A model that predicts a severe pollution event without explaining its atmospheric drivers is a black box, limiting its trustworthiness and utility for decision-makers who need actionable, causal insights. To address this critical gap, I propose a long-term research project to develop Causal-LLM, a new class of foundation models for spatiotemporal data that are both predictively powerful and causally interpretable. My central thesis is that genuine interpretability cannot be an afterthought; it must be designed into the model's core learning process. By adapting the powerful Time-LLM reprogramming framework and introducing a novel training methodology I term causal data synthesis, Causal-LLM will learn to not only forecast future states but also to articulate the human-understandable causal narratives behind them. This research will make two primary contributions: (1) a novel hybrid architecture that synergizes the perceptual power of GNNs with the reasoning capabilities of LLMs for complex physical systems, and (2) a new training paradigm that explicitly teaches this mapping. A successful project would provide a blueprint for a new class of trustworthy foundation models for science, enabling applications such as a climate model that not only predicts a flood but also explains the atmospheric river causing it, empowering authorities to make more informed and trusted decisions.

Woo Jon Hou Ainsley

Generative AI shows strong capabilities in language, reasoning, and code but remains prone to hallucinations—outputs that are fluent yet incorrect. In cybersecurity, such errors pose serious risks, from misleading analysts to potential adversarial exploitation. This project investigates hallucinations in three directions: (1) creating benchmarks and interpretability tools to characterize them in security contexts; (2) developing mitigation strategies such as retrieval-augmented generation, symbolic-neural hybrids, and uncertainty-aware decoding; and (3) integrating these methods into real-world workflows like vulnerability assessment, malware analysis, and penetration testing, while exploring how attackers might exploit hallucinations. Evaluation will combine accuracy metrics, human-in-the-loop studies, and red-team simulations. By bridging theory and applied system design, the work aims to advance understanding of hallucinations and improve the reliability of AI in cybersecurity, with broader implications for other high-stakes areas such as healthcare and law.

Emily Yu

The identification of unique traits and behavior is essential to providing personalized intervention in individuals with Autism Spectrum Disorder. However, the limited personalized quantitative data with experts' annotations in autism research pose a fundamental challenge to train AI models for unique behavioral patten discovery. Multiple Instance Learning (MIL) has demonstrated promising results in medical domains, where annotations are only needed at the group level (i.e., a whole sequence) instead of individual data instances. It provides a cost-effective way to train statistical models with limited labeled data. Additionally, the rise of pretrained models have shown great success in improving the performance in few-shot learning scenarios. In this proof-of-concept study, we propose a novel framework that integrates a transformer encoder pre-trained on large-scale spatiotemporal data with MIL, for unique behavioral pattern detection from autistic individuals. Our results demonstrated the discrimination of individual-level autistic behavioral differences and the accurate classification of behaviors across distinct groups: typically developing (TD) and autistic (ASD). Beyond aggregate performance metrics, we highlight visual insights from temporal instance scores, revealing interpretable differences between individuals in their respective groups. These results show promising progress towards tools that can be used for personalized intervention for autistic individuals, and more interpretable AI diagnostics.

Xiang Xue, Yatu Ji, Qing-Dao-Er-Ji Ren, Bao Shi, Min Lu, Nier Wu, Xufei Zhuang, Haiteng Xu, Gan-Qi-Qi-Ge Cha

Logit Knowledge Distillation has gained substantial research interest in recent years due to its simplicity and lack of requirement for intermediate feature alignment; however, it suffers from limited interpretability in its decision-making process. To address this, we propose implicit Clustering Distillation (iCD): a simple and effective method that mines and transfers interpretable structural knowledge from logits, without requiring ground-truth labels or feature-space alignment. iCD leverages Gram matrices over decoupled local logit representations to enable student models to learn latent semantic structural patterns. Extensive experiments on benchmark datasets demonstrate the effectiveness of iCD across diverse teacher-student architectures, with particularly strong performance in fine-grained classification tasks---achieving a peak improvement of +5.08% over the baseline.