As Large Language Model (LLM) agents scale toward real-world deployment, they generate large volumes of fragmented, non-standardized execution traces. Many existing observability platforms treat these traces primarily as passive logging artifacts, lacking the unified infrastructure to operationalize them for active governance and agent adaptation across heterogeneous single-agent and multi-agent workflows. To address this gap, we introduce TraceBrain, an open-source infrastructure for autonomous agent trace management. TraceBrain adopts a framework-agnostic architecture built on a delta-based OpenTelemetry (OTLP) schema, which mitigates context explosion and supports on-demand reconstruction of long-horizon execution trajectories. For runtime governance, TraceBrain implements uncertainty-driven supervision, where an internal Trace Evaluator prioritizes ambiguous trajectories for human review, thereby reducing manual annotation workload. Moving beyond passive observation, the platform incorporates a hybrid semantic-lexical retrieval engine that combines dense vector similarity and exact keyword matching for operational memory retrieval. Furthermore, an automated curriculum mechanism continuously synthesizes failure patterns into structured training artifacts. Empirical evaluations demonstrate a ~100x reduction in storage overhead together with high precision in uncertainty-guided trace supervision. Ultimately, TraceBrain transforms the execution history into a reusable operational memory substrate, bridging runtime observability with retrieval-driven agent adaptation. The system is publicly available at https://github.com/ToolBrain/TraceBrain.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
We present PhoMi, an interactive recall assistant that supports dementia reminiscence by engaging users with personal photographs captured via a live camera interface. Given a photograph, PhoMi delivers spoken questions and receives spoken responses, creating an accessible reminiscence setting with reduced reliance of human therapists. Over repeated sessions, user responses are incorporated into lightweight adapters of a vision–language model, enabling progressively personalized question generation without reprocessing prior interaction logs. PhoMi serves as a prototype toward scalable, lifelong AI companions for dementia reminiscence.
This paper describes a fully local, privacy-preserving intelligent system designed to assist in clinical psychology practice. The system automatically transcribes therapy sessions performing speaker attribution. Beyond transcription, the tool enhances clinical reasoning by detecting cognitive distortions and emotional patterns utilizing specialized deep learning classifiers and Large Language Models (LLMs). By guiding an LLM locally through a multi-step analysis process, the assistant synthesizes the enriched data and generates a series of analysis reports and clinical documentation of the session. As a result, the assistant reduces the administrative burden on professionals while preserving privacy with an edge computing approach in which the data never leaves the therapist's device. Finally, the assistant uses human-in-the-loop validation so that the professional always remains in control, ensuring clinical accuracy and trust.
DeepLog is an operational neurosymbolic framework that unifies logic and deep learning within standard PyTorch workflows. While existing neurosymbolic systems focus on a particular paradigm and semantics, DeepLog serves as a universal backend that can emulate many systems in the neurosymbolic alphabet soup. By treating diverse neurosymbolic languages as high-level specifications, the DeepLog software automatically compiles them into optimized arithmetic circuits. This design lowers the barrier for machine learning practitioners by treating logic as composable modules, while providing neurosymbolic developers with a shared, high-performance basis for prototyping new integration strategies. The code is available here: https://github.com/ML-KULeuven/deeplog
The increasing volume of hate speech on online platforms poses significant societal challenges. While the Natural Language Processing community has developed effective methods to automatically detect the presence of hate speech, responses to it, called counter-speech, are still an open challenge. We present PEACE 2.0, a novel tool that, besides analysing and explaining why a message is considered hateful or not, also generates a response to it. More specifically, PEACE 2.0 has three main new functionalities: leveraging a Retrieval-Augmented Generation (RAG) pipeline i) to ground HS explanations into evidence and facts, ii) to automatically generate evidence-grounded counter-speech, and iii) exploring the characteristics of counter-speech replies. By integrating these capabilities, PEACE 2.0 enables in-depth analysis and response generation for both explicit and implicit hateful messages.
Active learning reduces annotation effort by selecting informative samples, yet most approaches remain model-driven, offering users little control over training or support for understanding model behaviour. Human-centric active learning brings users further into the loop by introducing additional points of interaction, particularly in the sample selection process. However, such systems are typically demonstrated using fixed feature projections or visualizations of shallow classifier outputs. We present a representation-centric active learning tool in which interaction takes place directly within the model’s representation space. By operating in the same space the model uses for decision making, the interface supports the co-evolution of representations and user understanding. We additionally report initial qualitative (think-aloud) and quantitative findings from a pilot study, illustrating that such representation-centric frameworks can achieve comparable performance to standard baselines while fostering improved human–model collaboration. (Video and the code available at https://cst.dfki.de/demo-interacting-model-space)
Large-scale video repositories are increasingly available for modern video understanding and generation tasks. However, transforming raw videos into high-quality, task-specific datasets remains costly and inefficient. We present DataCube, an intelligent platform for automatic video processing, multi-dimensional profiling, and query-driven retrieval. DataCube constructs structured semantic representations of video clips and supports hybrid retrieval with neural re-ranking and deep semantic matching. Through an interactive web interface, users can efficiently construct customized video subsets from massive repositories for training, analysis, and evaluation, and build searchable systems over their own private video collections. The system is publicly accessible at https://datacube.baai.ac.cn/. Demo Video: https://youtu.be/L7bKfPBm2tU
We present a low-latency real-time audio game commentary system that generates spoken commentary directly from live gameplay video. In this end-to-end setting, a key bottleneck is accumulated waiting time; conventional pipelines capture frames, generate text, and synthesize speech sequentially for each utterance, and do not request the next generation until speech playback has completed. This strict sequentiality causes long and unnatural silence between utterances. To address this latency bottleneck, our system runs text generation in parallel with speech playback and buffers multiple candidate utterances ahead of time, enabling immediate synthesis at playback boundaries. Experiments on fast-paced game videos show that our parallel design reduces the mean inter-utterance silence from 9.6 seconds to 0.3 seconds compared to sequential baselines. It also improves similarity to professional speaking--silence timing patterns by over 40 %, and a user study with 120 experienced game players confirms significantly improved perceived speaking rhythm. Our demo video is available at: https://youtu.be/pmrRUlvav8M.
Forest imagery analysis often involves multiple tightly coupled vision tasks, which must be performed under substantial variation in geographic regions, sensors, and acquisition conditions. However, practitioners often lack a unified tool that is geospatial-native, cloud-optimized, and ML-integrated for end-to-end workflows spanning annotation, prediction, visualization, and downstream analysis at scale. We present AwakeForest, an interactive end-to-end platform designed for large-scale forest imagery that integrates model-assisted inference, automatic annotation, and human-in-the-loop refinement within a single workflow. Our platform supports plug-and-play integration of pretrained models and enables scalable interaction with forest imagery ranging from standard aerial scenes to large orthomosaics that can span several gigabytes to hundreds of gigabytes. AwakeForest produces analysis-ready outputs that can be directly used for downstream analysis and to support iterative model and annotation updates on new scenes. We demonstrate the system on the PALMS dataset and illustrate how AwakeForest supports an end-to-end workflow for practical forest management and analysis.
Passive Acoustic Monitoring (PAM), an increasingly popular method for wildlife monitoring, generates large volumes of data whose analysis depends on instance-level annotations that are costly to obtain. Archival sound collections provide weak labels that lack temporal localisation. In prior work, we demonstrated that Multiple Instance Learning (MIL) can extract approximate event locations from weakly labelled PAM data, suggesting it may be applied to sound collection data. This demo operationalizes that approach within an interactive workflow that connects weakly annotated sound collections to downstream PAM deployment. The system supports configurable MIL-based localisation, lightweight interactive refinement, and transfer to an independent PAM dataset. We carried out a preliminary evaluation with an actual sound library from a museum collection and a benchmark PAM dataset. Results confirm that weakly annotated sound collections can serve as a viable training signal for downstream PAM detection and illustrate differences between alternative MIL instantiations under real transfer conditions. (Video available at https://cst.dfki.de/projects-weak-supervision-demo)
We demonstrate ADP-MA (Autonomous Data Processing using Meta-Agents), a system that autonomously solves a complex and diverse set of data processing tasks. Three domain-agnostic meta-agents coordinate task-specific ground agents through a multi-stage pipeline: data understanding, planning, critique, expansion, execution, and finalization. Errors are caught early via progressive sampling on small data subsets before running on full data. The system supports three execution strategies, twelve domain knowledge packs, and confidence-based early stopping. An interactive web interface lets users watch pipelines being built in real time, replay completed runs at any stage, and compare results across cases. On four benchmarks, ADP-MA reaches 90.6% on DSEval, 44.8% on KramaBench, 50.0% on DA-Code, and 70.0% on AgentBench, outperforming published single-agent baselines.
In agricultural tasks, manual grape harvesting remains a labor-intensive activity facing challenges of efficiency, labor shortages, and sustainability. To this end, tailor-made robotic systems have been designed with the capabilities to transfer heavy boxes, navigate vineyard terrains, communicate, accurately locate, and safely interact with humans. The introduction of collaborative robotic fleets alongside human workers in large-scale vineyard harvesting effectively presents a Multi-Robot Task Allocation (MRTA) problem, where the real-world domain possesses characteristics that, when combined, pose a challenging research endeavor and align with open issues in MRTA research. Here, we present RoboVineSim, a simulation tool that can capture any vineyard area using geographical data and model the behavior of humans and robots in the environment. In addition, we have established the necessary mechanisms to facilitate the development of novel MRTA methods in this domain.
Event extraction is fundamental to information extraction. Prior approaches often separate event detection and argument extraction or depend on dataset-specific designs, limiting scalability and cross-domain generalization. We propose a unified generative, sequence-to-sequence framework that performs all event extraction subtasks jointly and supports both end-to-end and pipeline configurations. We fine-tune pre-trained language models on multiple event datasets across diverse domains, enabling a single model to retain domain-specific semantics while generalizing over large, evolving label spaces. Cross-domain experiments show strong, robust performance across datasets, demonstrating a scalable solution for real-world event extraction. We demonstrate these capabilities through a web-based application tailored for researchers and practitioners. The platform supports inspection of different configurations and facilitates cross-domain comparisons.
Semantic overlap challenges accurate agent routing in large-scale agentic systems. We present Intent Hub, a self-healing semantic agent routing system that combines offline asynchronous HITL repair with online Dual Filtering. LLM-generated positive and adversarial negative utterances help construct explicit decision boundaries, enabling interpretable millisecond-level routing. Intent Hub further supports interactive semantic debugging, allowing developers to diagnose conflicts, repair rules, and observe online routing changes.
Navigating the deluge of heterogeneous medical data, from academic literature (PubMed) to clinical guidelines (Web) and private knowledge bases remains a critical bottleneck for evidence-based medicine. While commercial black-box tools lack transparency, standard open-source RAG implementations frequently suffer from ``reasoning drift'' when handling complex, long-tail queries. We present DeepMed Search, a fully open-source, agentic platform designed for transparent medical deep research. Built on a high-performance Next.js architecture, DeepMed Search features a source-adaptive router that autonomously dispatches sub-queries to PubMed, web search, or local graph-based knowledge bases based on information density. Crucially, the platform integrates an introspective verification module, powered by a causal-consistent multi-agent debate framework, to validate retrieved evidence against diagnostic logic before synthesis. To demonstrate its robustness, we showcase DeepMed Search's ability to autonomously decompose high-difficulty rare disease queries, filter out confounding noise, and generate structured, citation-backed research reports in minutes. By open-sourcing this software, we provide the community with a robust infrastructure to democratize access to trustworthy, glass-box medical reasoning at a commercial-grade performance level, which is publicly available at: https://www.deepmedsearch.cloud and the demonstration video is available at: https://youtu.be/4U4aok8yLpk.
The transition from prompt-based Large Language Models (LLMs) to autonomous Deep Agents has enabled the automation of long-horizon tasks. However, as these agents adopt hierarchical architectures with nested tool usage, they suffer from significant opacity. Existing linear tracing tools fail to capture the multi-dimensional complexity of parallel sub-agent execution, hindering both debugging and user trust. We propose a general-purpose observability framework that decomposes agent execution into four distinct visualization dimensions: Temporal, Cognitive, Hierarchical, and Spatial. We validate this framework through RepoLearn, an open-source workbench for automated codebase comprehension. Our user study demonstrates that this multi-dimensional approach reduces the Time-to-Insight (TTI) for complex behavioral analysis by 56% and significantly lowers cognitive load (NASA-TLX) compared to state-of-the-art linear traces. The source code is available at https://github.com/amirkiarafiei/repo-learn and the demo at https://www.youtube.com/watch?v=s3U6E9o94gk.
We present Anti-Slavery Intelligence (ASI), a deployed AI system that analyses corporate modern slavery statements to identify compliance gaps and generate prioritised remediation advice. ASI orchestrates a multi-model pipeline: Gemini-2.5-Flash for vision-enhanced PDF parsing and structured compliance scoring against 48 expert-defined criteria, and Gemini-2.5-Pro for synthesising company-specific, timeline-based recommendations. A benchmarking engine compares each statement against industry and FTSE index averages across 11 sectors. Evaluation on 95 expert-annotated statements yields an F1-score of 0.86 and recall of 0.94, reducing time to generate an initial compliance assessment from several hours to approximately five minutes per document. ASI is publicly available at https://www.antislaveryintelligence.co.uk/ with free access for academics and NGOs. A demonstration video is at https://youtu.be/DNhdEGrRwzg.
We present an AI-powered interactive multimodal system that enriches digital image accessibility for blind and visually impaired (BVI) users. Our demonstration showcases two application domains: (1) an educational digital book, and (2) an online shopping interface. In both use-cases, users can virtually feel material textures (leather, wood, etc.) and engage in voice-driven inquiry about images. The system integrates state-of-the-art AI components – including voice-to-voice conversational agents, vision models for object segmentation, and a custom 16-actuator vibrotactile display – to provide multimodal feedback (haptic vibrations, spoken descriptions, and audio cues). The result is an inclusive technology with significant societal benefit, empowering BVI users to learn and shop more independently through natural multimodal interactions.
The increasing use of neural networks (NNs) in high-stakes decision-making requires rigorous analysis to ensure safety, fairness, and explainability. Formal verification tools for neural networks typically focus on determining the satisfiability of properties such as safety or fairness. However, many fairness and explainability tasks go beyond satisfiability and instead rely on arbitrary optimization objectives. To address such problems, neural networks are often encoded as mixed-integer linear optimization (MILO) problems with linear objectives. In practice, these encodings are usually implemented in an ad-hoc manner, limiting comparability across works, reducing transparency, and increasing implementation effort. We address this gap by introducing eNNcode, a user-friendly PyPI library that converts any piecewise-linear neural network in Open Neural Network Exchange (ONNX) format into a MILO instance. The library supports arbitrary constraints on input and output nodes, as well as user-defined optimization objectives. Our experiments show that eNNcode achieves performance comparable to existing libraries, despite its simplicity and ease of use. Overall, eNNcode facilitates reproducible and standardized optimization-based analysis of neural networks.
LLM-based mobile GUI agents usually invoke large models for nearly every micro-action, making real-device automation slow even when similar workflows have been completed before. We present vSpeedUI, a public demo system that turns past GUI experience into fast executable plans. It organizes historical trajectories into an Executable Experience Graph (EXG), where UI states are connected by Semantic Step Summaries with explicit preconditions. At task initialization, vSpeedUI performs Global Look-ahead Planning to retrieve, validate, and rank candidate transitions into a pre-verified plan. During execution, the agent uses lightweight graph traversal with state localization, target adaptation, and fallback when needed. On HarmonyOS, vSpeedUI reduces LLM latency and total task time while maintaining strong success rates, showing a practical route toward data-efficient GUI automation. Code is available at: https://github.com/LARS-research/vSpeedUI.