Review
-
BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines
2026-09-23 08:55:17Eranga Bandara, Xueping Liang, Asanga Gunaratna, Tharaka Hewa, Abdul Rahman, Peter Foytik, Safdar H. Bouk, Sachini Rajapakse, Isurunima Kularathna, Pramoda Karunarathna, Chalani Rajapakse, Ng Wee Keong, Kasun De Zoysa, Amin Hass, Wathsala Herath, Ross Gore, Ravi Mukkamala, Nihal Siriwardanagea, Gihan Siriwardanagea, Aruna Withanage, Nilaan Loganathan, Sachin ShettyAbstract
DNA sequencing pipelines, spanning quality control, alignment, variant calling, and annotation, are now reliably executed by workflow management systems that orchestrate established bioinformatics tools at scale. What remains manual is the decision layer surrounding that execution: selecting quality thresholds appropriate to a sample and platform, adjudicating borderline variant calls, diagnosing anomalies, and determining which findings warrant expert review. These decisions are repetitive, judgment-intensive, inconsistent across operators, and frequently undocumented. This paper introduces BaseCamp, a novel agentic AI framework for automating the decision layer of DNA sequencing pipelines. The framework decomposes the pipeline into six specialized AI agents, covering sample intake and quality control, alignment, variant calling, annotation, cross-stage monitoring, and reporting. Critically, BaseCamp agents do not perform sequence analysis: established tools execute alignment, calling, and annotation, while the agents select among them, configure them, interpret their output, and decide what follows. This confines language model reasoning to the judgment layer where it is reliable and preserves the reproducibility existing tooling guarantees. Agent reasoning is powered by a consortium of fine-tuned, domain-specialized large language models coordinated by a central reasoning LLM, executing locally so no sequencing data leaves the operating environment, under human-in-the-loop orchestration. Evaluation shows agent-generated configurations are concordant with expert practice, that an explicit filtering ledger renders inspectable what filtering otherwise removes without trace, and that cross-stage anomaly detection surfaces conditions execution monitoring misses. BaseCamp offers a generalizable blueprint for agentic automation of scientific data pipelines.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28557
PDF
-
NV-Reason-CT: 3D Visual Language Model for CT Analysis
2026-09-23 08:09:54Andriy Myronenko, Dong Yang, Yucheng Tang, Baris Turkbey, Benjamin Simon, Stephanie Harmon, Rikhil Makwana, Mariam Aboian, Sena Azamat, Ibrahim Ethem Hamamci, Sezgin Er, Bjoern Menze, Marc Edgar, Yufan He, Pengfei Guo, Daguang XuAbstract
We present NV-Reason-CT, a generative vision--language model for chest and abdominal CT combining native 3D visual encoding with radiologist-guided reasoning. The model couples a native 3D vision transformer with a language model, passing all visual tokens and their explicit 3D coordinates into language decoding without further spatial token merging. This retains volumetric spatial information within the vision encoder and through the language model's positional encoding during joint processing with text. We train on a curated corpus of approximately 550,000 multimodal instruction examples from 70,111 unique CT image inputs, combining standardized reports, abnormality-focused and anatomy-specific questions, multi-turn interactions, and radiologist-authored reasoning from recorded and transcribed expert CT interpretations. Expert annotations provide direct supervision and guide additional report-grounded synthetic reasoning. End-to-end supervised fine-tuning (SFT) is followed by Group Relative Policy Optimization (GRPO), with verifiable rewards over chest and abdominal abnormality sets. The model supports abnormality classification, report generation, and interactive reasoning with reviewable observations, differential diagnoses, and uncertainty. Evaluation spans public CT benchmarks and a held-out NIH cohort. On CT-RATE, NV-Reason-CT achieves a macro-F1 of 0.614 and macro-AUROC of 0.871 without a task-specific classification head; generated reports achieve a report-derived macro-F1 of 0.592. In a preliminary study with expert radiologists, AI-assisted review received favorable confidence ratings and was associated with a 50% reduction in average reported interpretation and reporting time. We release the model and training code to support reproducible research on explainable AI for volumetric medical imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27511
PDF
-
EviStreams: Human-in-the-Loop AI Data Extraction for Systematic Reviews in Medicine
2026-09-23 06:35:07Sai Karthik Kosuri, Ankita Shashikant Bhosale, Michael Glick, Alonso Carrasco-Labra, Chris Callison-BurchAbstract
Systematic reviews underpin clinical guidelines, yet their data-extraction step is a major expert-labor bottleneck bound by a protocolized workflow: two reviewers extract each study independently, an adjudicator resolves disagreements, and the team keeps an auditable record of how every value was produced. Large language models can assist with extraction, but that assistance must fit established review protocols and preserve reproducibility. We present EviStreams, a live, open-source, no-code web platform that puts review teams in control of AI-assisted extraction at three key stages: program design (a structured decomposition approved before any code runs), field specification (typed field definitions calibrated from a pilot), and extracted predictions (reviewer-blinded dual review with adjudication). Working through a form builder, a domain expert defines typed fields rather than prompts, runs extraction over uploaded PDFs, inspects every value alongside the supporting passage it came from, and resolves a reviewer-blinded dual review into an auditable consensus export. An evaluation across four clinical corpora and three frontier model families, released with the system, shows that extraction quality is shaped far more by the field specification than by the choice of model. EviStreams is live at this https URL and released under Apache-2.0.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27418
PDF
-
Emergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
2026-09-23 06:34:02Haoluan Fu, Keni Chen, Xinyu Jia, Jinpeng Wang, Yuyu YinAbstract
Symbiosis between humans and digital beings offers a vision for the future of human--machine interaction. In enduring human--machine relationships, personality provides a foundation for continuity of identity, individuality in interaction, and development through experience. We investigate this capacity through persona agents as computational implementations and introduce Emergi-PersonaOS, a psychology-grounded operating system for managing persona objects throughout their lifecycle. The system organizes dispositional traits, characteristic adaptations, and narrative identity into a three-layer persona representation, distinguishing relatively enduring persona beliefs from their activation in the current persona state. During situational adaptation, it integrates the current interlocutor, relationship, event, and retrieved memories to infer a persona state and generate actions and replies; during long-term development, it records experiences and outcomes, and develops and evaluates revision candidates through change attribution, meaning-making, and behavioral testing. Belief updates are managed through explicit review, traceable evidence and version records, and the ability to reject candidates, making persona evolution controllable. Using television-character dialogue as longitudinal material, we demonstrate long-horizon system operation and examine its principal mechanisms in a concrete implementation. This work provides a computational framework for persona agents to maintain individual continuity, produce situation-specific expression, and develop through experience over sustained interaction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27417
PDF
-
Automated Extraction of Records of Processing Activities Using Hybrid RAG and Locally Deployed Large Language Models
2026-09-23 04:55:53To Duy Hinh, Nguyen Le Quoc Anh, Phan Van Tri, Khuong Nguyen-AnAbstract
Vietnam's Personal Data Protection Law (Law No. 91/2025/QH15) and Decree No. 356/2025/ND-CP, effective January 1, 2026, require organizations to establish and maintain Records of Processing Activities (RoPA). Manual RoPA preparation is labor-intensive, while cloud-hosted large language models (LLMs) may conflict with data-sovereignty requirements. We propose RoPA Manager, a system for automated RoPA information extraction using hybrid retrieval that combines lexical ranking over tsvector, dense-vector search, Reciprocal Rank Fusion (RRF), and locally deployed LLMs. We introduce a Vietnamese RoPA benchmark with 32 organizations, 77 processing activities, 12 field groups, and 4,338 reference values. Evaluation is reported at three distinct levels. The automated scorer, tested on perturbed data without invoking an LLM, achieved F1 = 0.9493 [0.9436, 0.9548]; this measures scorer robustness rather than end-to-end extraction accuracy. End-to-end extraction achieved token coverage of 50.04-55.25% against the reference labels. Two independent experts reviewed 1,558 reference values (35.9% of the benchmark), found no incorrect values, and achieved 99.68% agreement with PABAK = 0.9936. Value-level precision was not measured. Across 32 paired scenarios on a 24 GB GPU, locally deployed Qwen3.5-27B-GPTQ-Int4 showed no statistically significant difference from cloud-based DeepSeek-V4-Flash (difference 0.20 percentage points in favor of DeepSeek, 95% CI [-0.93, 1.32], p = 0.72), while Gemma-4-31B performed significantly worse (p < 0.01).
Abstract (translated)
URL
https://arxiv.org/abs/2609.27359
PDF
-
CART: Closed-Loop Adaptive Red Teaming for Large Language Models
2026-09-23 04:16:46Dongdong Zhang, Tengchao Lv, Yilin Jia, Yuzhong Zhao, Yupan Huang, Wenshan Wu, Xiangyang Zhou, Shaohan Huang, Nan Yang, Li Dong, Lei Cui, Furu WeiAbstract
Automated red teaming often replays a fixed set of prompts, which measures known risks but cannot learn from failures found during testing. We present CART (Closed-Loop Adaptive Red Teaming), a framework that uses each result to guide what it tests next. CART begins with broad risk coverage, follows weaknesses that emerge, keeps new probes diverse, and records the evidence and source of every finding. It separates the Challenger that creates tests, the Target being tested, which may be a text-only model or a bounded tool-using agent, and the Judge that evaluates the results, allowing these roles to be studied independently. Across three evaluation families (Frontier, JAH, and Agentic), CART discovers more failures and higher average risk than static seed replay for every Target with an available baseline. The gains extend to tool-mediated agent tests, suggesting that contextual adaptation can reveal weaknesses that direct prompt replay does not exercise. These results describe what the test policies discover, not how often failures occur in real deployments. We also find that Challenger-Judge choices affect the evidence uncovered, highlighting the need for role separation and independent review. Overall, CART turns red teaming from a one-time checklist into a continuous, adaptive, and auditable search for model and agent weaknesses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27336
PDF
-
PAWS: Policy-driven Agentic World Simulation
2026-09-23 03:51:01Tiviatis Sim, Jia Hui Woon, Xinming Gao, Chen Gao, Fengbin Zhu, Zheng Huanhuan, Chua Tat Seng, Kenji KawaguchiAbstract
Policy interventions propagate through public communication, institutional decisions, and stakeholder responses, yet datasets for financial multi-agent simulation rarely connect these processes to temporally aligned historical evidence. We introduce PAWS, a Policy-driven Agentic World Simulation dataset covering 36 verified U.S. financial and economic policy episodes, 12,727 policy-linked news records, and 65,291 source-grounded stakeholder actions. Each action is linked to its supporting news and represented by a multi-layer event frame capturing its interaction mode, financial-action family and subtype, semantic attributes, and conditional mappings to external taxonomies. Entities are resolved to normalized organizations, and actions are aligned with daily market-return context to support policy-agent simulation replay. On 2,522 stratified action samples, independent AI and human reviewers achieved 89.4% initial agreement on interaction mode, with disagreements subsequently adjudicated. Case studies of the 2008 short-selling ban and 2001 decimalization recover documented policy timelines and associated market patterns across both dense and sparse news settings. A replay study further shows that high accuracy can mask failure to detect rare stakeholder actions, identifying action timing and calibration as central challenges. PAWS provides an auditable substrate for evaluating agent influence, policy-response cascades, and action-outcome alignment in historically grounded financial simulations.
Abstract (translated)
URL
https://arxiv.org/abs/2609.28547
PDF
-
UniDataAgent: An Ontology-Grounded Agent for Enterprise Question-to-Report Automation
2026-09-23 02:42:34Yutai Duan, Yahui Zhao, Zhangti Li, Yu Ma, Zhenfeng Qi, Shaoyang Yuan, Jing Fan, Jie LiuAbstract
Enterprise data agents must preserve organization specific semantics, not just translate questions into queries. We present ChinaUnicom DataAgent (UniDataAgent), an ontology grounded system for reusable question-to-report analysis that separates semantic acquisition from online execution. Ontology Acquisition and Validation stage (OAV) builds versioned enterprise ontologies from metadata, business knowledge, and supporting materials through expert authored business skills, constrained generation, question verification, and selected expert review. Question-to-Report Execution (QRE) stage retrieves semantic contracts for each question, coordinates skills and data tools, validates results, and produces evidence linked reports. Across 27 enterprise tables and roughly thousands of metric types, ontology construction took a few hours instead of about one week manually. It took just a few minutes to generate the reports, instead of several working days. Ontology grounding achieved 95.0\% strict accuracy on real business questions, versus 72.5\% for document RAG, especially on structured and compositional tasks. The system has already been deployed to generate cost savings and has the potential to be replicated in other enterprises.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27257
PDF
-
Self-Evolving Multimedia Verification through Memory Consolidation of Contestation Experiences
2026-09-23 00:18:36Truong Thanh Hung Nguyen, Vo Thanh Khang Nguyen, Hoang-Loc Cao, Phuc Ho, Truong Thinh Nguyen, Van Pham, Hung CaoAbstract
Multimedia verification requires not only accurate decisions but also traceable evidence, reliable human correction, and safe reuse of prior experience. Existing systems often lack explicit mechanisms for revising intermediate reasoning or preventing harmful knowledge transfer. We present SEMV (Self-Evolving Multimedia Verification), a self-evolving multi-agent framework that treats provenance-bearing arguments as the interface between evidence, reasoning, human contestation, and memory. SEMV combines arena-based quantitative bipolar argumentation (A-QBAF), causal and scoped revision, and verification-gated memory consolidation with explicit conflict retention. On COSMOS benchmark, SEMV achieves 91.88% accuracy versus 89.10% for the strongest comparable baseline. Verified memory reduces negative transfer from 5.7% to 0.2%. On CTR benchmark, constructed from reviewer contestations, scoped causal revision corrects 96.7% of initial errors while saving 52.8% compute. MV2026 Grand Challenge dataset further supports evidence-grounded, temporally consistent reporting. These results show that SEMV can evolve through verified experience while keeping accumulated knowledge and subsequent decisions traceable, revisable, and contestable.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27175
PDF
-
Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit
2026-09-22 21:39:06Kabeh Mohsenzadegan, Vahid Tavakkoli, Kyandoghere KyamakyaAbstract
Organizations increasingly use LLMs for policy, compliance, risk, and operational decision support, requiring evidence validation, review routing, version control, and auditability. We introduce Policy-as-Skill (PaS), a modular runtime that packages these functions as executable, versioned policy capabilities. Thirteen methods are evaluated with a fixed Gemma4 backend on 600 development tasks. PaS+Audit achieves 53.8% exact accuracy, macro-F1 0.346, review F1 0.854, citation precision 1.000, policy-reference recall 0.984, and audit completeness 1.000, outperforming LLM+RAG on most governance and review metrics. Deterministic control raises aggregate accuracy to 61.2% but is strongly task dependent, supporting selective rather than universal rule-based intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27087
PDF
-
ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts
2026-09-22 19:57:19Luis Sante, Paula Lima, Mariana Rocha, Jorge PocoAbstract
Legal contracts are structurally complex documents in which contradictions may emerge across distant and interconnected provisions. Although large language models (LLMs) improve legal language understanding, contradiction analysis remains a human-centered and evidence-grounded review task. We present ContraVis, a visual analytics system for human-in-the-loop contradiction analysis in legal contracts. The system models contracts as typed paragraph graphs that combine explicit contractual references with semantic relationships between paragraphs. This graph plays a dual role: it conditions LLM reasoning and serves as the interactive representation the analyst explores, keeping model context and human inspection aligned across coordinated views. In a controlled comparison, graph-conditioned reasoning recovered more injected contradictions than standalone LLM analysis as contract length grew, while surfacing additional candidates for analyst validation. A formative study with contract-domain lawyers indicated that in-context evidence comparison supported contradiction validation, and we distill design implications for evidence-grounded, LLM-assisted document review.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27014
PDF
-
Designing and Analysing Argument Mining Pipelines: Towards a Comprehensive Assessment
2026-09-22 12:46:29Siddharth Bhargava, Sara Tonelli, Patricia Mart\'in-RodillaAbstract
Argument Mining (AM) transforms natural language into its underlying argument structures. This transformation is typically realized through a sequence of AM tasks that form an end-to-end AM pipeline. However, AM approaches often differ in how they conceptualize these tasks, making direct comparisons between them difficult and opaque. This calls for a more nuanced, task-level analysis of AM approaches to enable clearer comparison and assessment. This work presents a preliminary meta-study that systematically reviews several state-of-the-art end-to-end AM works and analyzes their pipelines through a triple-perspective framework---a linguistic, computational and domain perspective---to understand how the pipelines model arguments as structures, computes them, and integrates domain knowledge. We further propose a general design to the linguistic and computational perspectives, illustrating how key AM tasks are designed for modeling and computation of argument structures. Our proposed framework lays the groundwork for methodology-centered descriptions across AM approaches, facilitating deeper understanding and more systematic comparisons in future research.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26338
PDF
-
CHiME-9 ECHI: A Machine Learning Challenge for Enhancing Conversations to Address Hearing Impairment
2026-09-22 12:13:53Robert Sutherland, Thomas Kuebert, Marko Lugger, Stefan Petrausch, Eline Borch Petersen, Juan Azcarreta Ortiz, Buye Xu, Stefan Goetze, Jon BarkerAbstract
This work presents the task and results of the CHiME-9 challenge for Enhancing Conversations to address Hearing Impairment. The challenge considers the scenario of four-party conversations in a noisy, cafeteria-style environment with interfering speech sources and sound effects. Participants are provided with audio recordings made with Meta Aria glasses and hearing aid microphones, and clean speech samples of the conversation participants. The task is to extract the speech of the conversation partners from the noisy multi-channel recordings with the goal of improving the intelligibility and quality of the speech, evaluated using objective metrics and subjective listening tests. This paper reviews submissions from seven teams and ranks them on a combination of subjective intelligibility and quality. Results show that while the objective metrics do not reflect listener performance, the top systems were able to make substantial improvements over the challenge baseline in both intelligibility and quality ratings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.26306
PDF
-
ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents
2026-09-22 06:18:25ScholarSeed AI Team, Caoqinwei Gong, Xue Jiang, Wei Luo, Xiaoyu Qiu, Jiayi Sheng, Yi Wang, Zheng Yu, Ao Zhang, Haifan Zhang, Hanwei Zhang, Jihai Zhang, Yuan Cao, Wei Chen, Liyun Dai, Wenkai Fang, Guanglei Wang, Kai Ying, Tingyu Zhu, Wotao YinAbstract
Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim assessment. Most existing systems, however, are organized around individual tasks: the same papers are repeatedly retrieved, segmented, and interpreted, and the understanding built in one task is difficult to reuse in the next. We present ScholarStack, a layered research asset framework that compiles a paper collection into reusable, versioned, and provenance-preserving assets at three complementary levels: source-grounded paper-level statements, domain-level organization, and evidence-grounded cross-paper syntheses. A common access interface returns task-specific views at the evidence granularity each task requires, preserving study conditions, source traceability, and verification status. We instantiate the framework on four task families spanning ten task settings, comparing agents that use the compiled assets with task-specific baselines under matched base models. Quality gains concentrate on tasks that require cross-paper evidence, such as multi-paper question answering and literature review generation, and query-time token cost falls on every task where it is measured, with assets compiled once and reused across tasks. These results suggest that layered research assets can serve as shared infrastructure for scientific agents, shifting literature-based assistance from isolated document processing toward cumulative, evidence-grounded workflows.
Abstract (translated)
URL
https://arxiv.org/abs/2609.23735
PDF
-
Zephyron: Integrated Design and Analytical Evaluation of a Solar-Assisted Mobile Manipulator for Multimodal Environmental Reconnaissance and Distributed Visual Inference
2026-09-22 05:28:19Sabik Bin Sultan, Shafi Bin Sultan, Safwan SadadAbstract
Environmental reconnaissance needs mobile platforms that carry sensors, preserve measurement context, and return interpretable evidence under limited energy and communication. We present a literature-informed engineering design for Zephyron, a four-wheel rover with a front manipulator, environmental sensors, distributed computer vision, local recording, and a raised rear solar module. The design keeps the prototype layout but replaces unsupported numerical assumptions with an explicit component and geometry baseline. A reproducible search retrieved 5,000 records (4,858 unique) for screening, followed by targeted review of primary literature and manufacturer documentation. The baseline uses 165 mm wheels, a 12 kg mass budget, a 72 Wh battery-energy basis, and a 20 W photovoltaic module. With rolling-resistance coefficient 0.04, steady ascent of a 10 degree grade needs about 0.517 N m per wheel under equal load sharing. An illustrative 40 W motion load gives 1.44 h from 57.6 Wh usable energy, and a 25 percent driving duty gives 4.19 h without solar input; these are calculated scenarios, not measured performance. Sensor models show how integration time, calibration, temperature, and communication delay constrain interpretation, and a quality-aware stop-and-sample policy links these constraints to mission execution. Lightweight detectors, reference-based sensor learning, and executable data-integrity checks define a reproducible machine-learning evaluation pathway. The contribution is a traceable design and evaluation framework with editable 3D models, subsystem diagrams, and reproducible analytical data. Experimental validation is required before assigning payload, endurance, detection, or field-operating ratings.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25709
PDF
-
Teaching Reinforcement Learning and Humanoid Robotics to High-School Students: An Expert-Validated Curriculum Design on a Low-Cost Open Platform
2026-09-22 04:27:06Yuanzhe Dong, Jie Cao, Shuman WangAbstract
Lower cost open source robots and reinforcement learning (RL) simulation tools create new opportunities for precollege students to engage with contemporary robotics. However, translating a complete research workflow, spanning mechanical assembly, electrical setup, simulation, policy learning, system identification, and physical deployment, into a coherent course for novice learners remains challenging. We present an integrated robotics course framework that organizes these activities around a shared robotic artifact. The framework combines parallel disciplinary tracks, sequencing based on technical dependencies, progressive integration of simulation and hardware, layered performance checkpoints, and structures for balancing collaborative work with individual accountability. We illustrate the framework through a high school curriculum organized around a robot project in which pairs of students assemble an open source humanoid robot, train a walking policy in simulation, and deploy it on the physical platform. The framework was developed through an iterative design process that included formative review by five experts in robotics research, engineering, secondary STEM education, and curriculum design. Expert feedback highlighted three central design tensions: authenticity versus cognitive load, system integration versus timely visible progress, and team construction versus individual accountability. These tensions informed the final framework presented in this paper. This work offers a structured approach for adapting robotics research workflows into interdisciplinary precollege courses; future classroom studies are needed to examine implementation and student learning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25674
PDF
-
Skill Sequence Planning for Collaborative Multi-Robot Construction
2026-09-22 03:59:12Xi Wang, Bo Fu, Carol C. Menassa, Vineet R. Kamat, Min DengAbstract
Robots have significant potential to automate construction processes. However, their industry adoption remains limited, partly because of the programming effort required to adapt robots to diverse tasks. This paper presents a skill sequence planning method that enables a heterogeneous team of multi-functional robots to collaboratively perform construction assembly work using reusable, preprogrammed skills such as grasping, drilling, and fastening. A central controller transforms the digital representation of the building into a construction relationship graph that represents construction entities, their states, and their parent-child relationships. Based on this representation, the system selects the next construction target, generates a symbolic sequence of skills for capable members of the robot team, and produces collision-free geometric motion plans for skill execution. The symbolic planning problem is dynamically regenerated as the construction state changes. An interactive digital twin presents the planned skill sequence and robot states to human co-workers for review and approval before execution. The method is evaluated through a construction assembly case study. By reducing the need to program robots separately for each task variation, the proposed approach supports more flexible deployment of collaborative robot teams in construction.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25649
PDF
-
Evidence-gated multimodal parsing and vectorization of architectural floor plans
2026-09-22 03:21:55Hongxuan Chen, Wenda Wang, Jiachen Lu, Qirui Shen, Zilong Huang, Lei He, Xinyue Dong, Weixin HuangAbstract
Architectural floor plans remain a high-friction barrier to archive digitization and early design-model preparation because heterogeneous graphics encode spatial semantics and editable geometry together. We introduce SALI-FP, an evidence-gated multimodal pipeline that converts a plan into reviewable semantic maps, objects, vectors, and relation records while constraining local revisions by image evidence. In a full production audit of 11,534 heterogeneous plans, SALI-FP produced structured outputs for every plan, including 752,510 valid polygon-bearing objects. The same output form has supported initial drawing digitization and design-model preparation in practical design work. Public-benchmark calibration is paired with a 30-case matched visual evidence set in Appendix F, where room-scale coverage, openings, oblique boundaries, and circulation continuity can be inspected directly. SALI-FP offers an engineering-oriented interpretation-to-geometry workflow for reviewed CAD/BIM preparation and existing-building information recovery.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25615
PDF
-
mbariml: a curation pipeline for turning deep-sea imagery and video into object-detection training data
2026-09-21 23:57:55Lonny Lundsten, Kevin Barnard, Dave CaressAbstract
Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection models on video and images from the deep sea, in which the objects of interest, primarily organisms, are sparse, faint, and hard to identify, incremental improvements to object detector performance may require an iterative approach to data labeling and management. This paper presents mbariml, a python-based video and image analysis pipeline built around the data labeling management process. mbariml uses an Ultralytics YOLO detection model, runs it over still images or video, stores every detection as a reviewable region of interest, groups those regions by visual similarity so that a human can accept or reject them in bulk, and exports the result as training data, statistics, image sidecars, and additional metadata. The human review stage is the centre of the design: an annotator can validate, relabel, resize, delete, and draw entirely new localizations, and every one of those edits is written back to the same database the detector wrote to. Video receives particular attention: the software treats each tracker-produced track as a provisional observation and selects one representative frame instead of retaining every detection in the track. We describe the pipeline stage by stage, including the operational middle-third heuristic used for track observation selection.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25500
PDF
-
Passes Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development
Abstract
Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We study these failures with stale, a benchmark for semantic coordination. Our evaluation runs the same tests on each patch alone and on their combination, counting only failures introduced by combining the patches. We use three tiers: synthetic tasks with controlled interface changes, pairs of merged pull requests, and constructed tasks that use real Django helpers. Among 834 runs on 417 mined Django pairs, only one showed interference after correcting the grading procedure. On constructed tasks using 12 Django helpers, interference occurred in 97% of runs. A message describing the completed concurrent change recovered 82% of runs. Reviewed pull requests may contain few unresolved parallel changes, even when agents fail on controlled tasks using real code. The constructed failure rates do not estimate how often these problems occur in practice.
Abstract (translated)
URL
https://arxiv.org/abs/2609.25396
PDF
