Detection
-
When Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback
2026-10-06 10:28:19Kavienan Jegatheesan, Gayathri LihinikaduarachchiAbstract
Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail silently, returning plausible but incorrect results. How well can agents detect and correct corrupted tool call outputs? We study this through a controlled corruption framework where a hidden interceptor replaces tool call results with plausible incorrect information on targeted problems. We evaluate agents across 31 problems under four verification designs including no verification (baseline), mandatory same-context reflection, optional fresh-context verification, and optional structural verification. Without verification, corruption causes dramatic accuracy loss, from 100% down to 72.4%. Mandatory reflection fully recovers this performance to 100%. Optional verification improves accuracy only when models actively invoke it. Our results show that checking frequency is strongly associated with robustness differences, while unequal invocation prevents a controlled comparison of verifier quality. A supporting recovery experiment shows that full problem restart succeeds in 100% of cases after explicit detection. These findings demonstrate that verifier availability and verification policy are separate components of mathematical-agent reliability. Mandatory policies enforce verification while optional policies depend on the model's own choice to invoke it.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08097
PDF
-
The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation
2026-10-06 09:19:10Jorma Valjakka, Juhani Kivim\"aki, Juha Myll\"ari, Jukka K. NurminenAbstract
In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked with open-domain question answering (QA) datasets containing questions and corresponding short reference answers. First, an LLM is used to generate answers to questions within the QA dataset. Then, some automated labeling strategy is used to label these answers as hallucinated or not by comparing them with the reference answers in the dataset. This evaluation setting creates a methodological ambiguity between two criteria: reference faithfulness (whether the answer is fully supported by the reference) and factual correctness (whether the answer is free from contradictions and factually false specific claims). In practice, automated labelers may apply the former criterion even when the intended target is the latter. We study this potential criterion mismatch using 900 human-labeled question-answer pairs spanning three commonly used QA datasets and three generator models, with labels targeting answer-level factual correctness. We evaluate lexical similarity metrics, a reference-entailment NLI baseline, and seven LLM judges under controlled prompt variants as automated labelers. Our experiments reveal substantial disagreement both among automated labeling strategies and between these labels and human annotations. Many strategies also exhibit strong directional error biases, and for most judge-generator pairs, replacing a faithfulness-oriented prompt with a factual-correctness prompt improves agreement with human annotations and reduces false-positive dominance, indicating that automated hallucination labels depend strongly on how the target criterion is specified. Label-source choice should therefore be considered a fundamental part of benchmark design and made explicit, validated, and matched with the benchmark goal.
Abstract (translated)
URL
https://arxiv.org/abs/2610.08026
PDF
-
M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding
2026-10-06 08:45:25Jinsong Zhang, Kejun Wu, Ming Zhu, Renjie Qiao, Chengtao Cai, Zhengguo LiAbstract
Monocular metric depth estimation and 3D visual grounding represent the two complementary cornerstones of monocular 3D spatial understanding (M3Sun), from which the fundamental 3D spatial information required by M3Sun can be acquired. However, these complementary tasks are generally conducted by separate frameworks, which pose challenges of inflexible and unaligned spatial information access for embodied intelligence systems. In this paper, we propose a unified agent for monocular 3D spatial understanding (M3SunAgent) that leverages a large language model (LLM) as a task planner for spatial visual programming, which flexibly generate structured programs and coordinate tools. For instance-level metric depth estimation task, M3SunAgent invokes an object detector tool to locate the target, estimates depth at selected points with a depth estimation tool, and aggregates these predictions into an instance-level depth estimate. We also construct the M3Sun Instance (M3SI) dataset, a benchmark with 2,910 samples for evaluation. For monocular 3D visual grounding task, M3SunAgent uses a vision-language model (VLM) tool to locate the target and output basic spatial attributes, then combines back-projection tool with a dimension-lifting tool to predict its 3D bounding box. Experimental results demonstrate the superior performance of M3SunAgent. Specifically, in evaluations of instance-level monocular metric depth estimation, M3SunAgent achieves the best performance among all compared models, 52.61% of predicted instances are distributed below depth error 0.25 ($\delta < 0.25$). In evaluations of monocular 3D visual grounding, M3SunAgent demonstrates overall competitive performance than vision and VLM models, reaching a 3D mean intersection over union (mIoU) of 41.73% and exceeding the state-of-the-art MonoVLM model by 3.62%.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07982
PDF
-
CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage
2026-10-06 08:13:10Baptiste Chopin, Thomas Swearingen, Arun Ross, Antitza Dantcheva, Christian RathgebAbstract
Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both human viewers and automated synthetic video detectors. Since these tools are so widely accessible, a malicious user can create a harmful video clip at minimal cost. The production and dissemination of such videos in high-stakes settings, such as crime reporting and elections, can misdirect emergency response efforts or distort political discourse. Existing deepfake video datasets, used by the research community to develop deepfake detection algorithms, exhibit two limitations: (1) they emphasize benign web content rather than footage of possibly malicious activity, and (2) they rely on older or open-source generators that do not represent recent advances in generative systems. We assemble CCtv DeepFakes (CCDF), a video deepfake dataset, to address both gaps. CCDF contains 1840 videos (460 real and 1380 generated) spanning 16 crime and accident categories, with generated content produced using three leading commercial systems: Grok Imagine, Google VEO 3.1, and OpenAI Sora 2. CCDF is a highly realistic, small-scale, manually annotated dataset targeting evaluation of detection models. We release three versions of the dataset: the raw generated data, a cleaned version in which video metadata are standardized between real and synthetic samples to prevent detectors from exploiting trivial cues, and an altered version simulating low-effort post-processing attacks. We evaluate CCDF with ten recent state-of-the-art detectors covering different detection approaches. Our results suggest that these approaches do not reliably distinguish CCDF's generated videos from real ones, despite their strong reported performance on existing datasets. These results further confirm that existing datasets are not well-suited to evaluating certain threats.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07939
PDF
-
LoDEOT: Low-Dimensional and Efficient Offset Tokens for Building Footprint Extraction from Off-Nadir Imagery
2026-10-06 06:38:44Kai Li, Zigan Zhou, Zhenyang Li, Hui Shan, Zhe Chen, Yupeng Deng, Zhihao Xi, Yu Meng, Yifan Peng, Xiangyu ZhaoAbstract
Instance-level roof-to-footprint offset (RFO) prediction is central to extracting building footprints from off-nadir imagery. Query-based pipelines commonly use high-dimensional instance tokens to predict signed two-dimensional RFOs. We investigate whether RFO prediction can instead use a compact offset token. Under local pinhole projection and vertical-extrusion assumptions, the idealized RFO map admits a five-parameter sufficient descriptor comprising intrinsic shape, composite amplitude, and relative geometry. This factorization provides a structural prior for a five-dimensional offset token, whose channels learn task-relevant latent representations through end-to-end training. Based on this design, we propose LoDEOT, which retains high-dimensional instance tokens for detection and segmentation but maps instance-token, concentration-gated roof, and box-mask evidence to a five-dimensional offset token followed by an independent two-dimensional readout. Known denoising-query target indices further align each supervised decoder-layer estimate with the same clean instance RFO, organizing successive predictions as target-aligned recovery under perturbed query conditions. Experiments on five real-world building datasets demonstrate the effectiveness of LoDEOT for building footprint extraction. Experiments on real-world building datasets demonstrate that a five-dimensional offset token can support accurate RFO prediction. On BONAI, LoDEOT achieves the best roof-detection bAP and bAP50 and leads all five offset-corrected footprint metrics among the evaluated end-to-end methods, with FAP50 of 54.58 and mEPE of 5.23 pixels. Its FAP50 exceeds those of the evaluated end-to-end baselines by 7.56-16.85 percentage points.
Abstract (translated)
URL
https://arxiv.org/abs/2610.05899
PDF
-
Towards benchmarking Western Bluebird detection in the wild
2026-10-06 05:56:05Estela Monserrat Arriaga Santana, Julian Rosas Scull, Ibeth P. Alarc\'on, Bibiana Montoya, Aylin Sosa Mej\'ia, Hugo Jair EscalanteAbstract
Bird monitoring in natural environments is challenging due to the small size of some species of birds relative to the scene, background clutter, variability in illumination, and the observers' viewpoint. Progress is further limited by the scarcity of large-scale, realistic datasets, which are essential for understanding behavioral patterns. To address this gap, we introduce a new benchmark dataset for the detection and segmentation of Western bluebirds (Sialia Mexicana), comprising over 6,000 labeled images from 41 recording sessions. The dataset features high-resolution (4K) in-the-wild images in which birds occupy only a small fraction of the image. We evaluated supervised detectors, open-vocabulary models under zero-shot and fine-tuned settings, and segmentation approaches. Supervised detectors remain the most reliable overall, with Faster R-CNN achieving the highest detection mAP and RT-DETR offering the best precision-recall trade-off. Open-vocabulary models perform poorly in zero-shot settings; however, fine-tuning substantially improves their performance, with YOLO-World becoming competitive with supervised methods and achieving the highest precision, F1-score, and mAP@0.5. For segmentation, supervised methods significantly outperform Grounded-SAM and SAM 3: Mask R-CNN achieves the highest mask mAP, while YOLOv8-Seg provides the best precision and fastest inference. A diagnostic analysis further shows that failures are not explained by object size alone, but by a combination of apparent scale, brightness, contrast, clutter, blur, crowding, and recording-session variation. Overall, our findings highlight the difficulty of zero-shot bird detection in cluttered ecological scenes and underscore the importance of domain adaptation in small-object settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07802
PDF
-
Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell
2026-10-06 05:17:44Hochan Son, Kyungdoe Han, Jaehan Koh, Xiaowu Dai, Wenlu Xu, Guang ChengAbstract
Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds. Many such systems add a persistent tier storing and recalling reasoning traces, usually validated by an ablation reporting an accuracy gain. We measure both on one three-tier agent architecture. Decomposition delivers: peak KV working set of 14.3 MiB per query against 35.5 and 35.3 MiB for single-pass and retrieval-augmented baselines. The persistent tier does not: across eight controlled dataset pairs at n=100 per arm it costs +0.368 MiB [+0.167, +0.590] of peak cache and produces no detectable accuracy change (+0.015, 95% CI [-0.011, +0.046]). We argue the null is structural: single-question benchmarks supply each item with its own evidence and score it independently, and correctness requires resetting stored traces between conditions, so recall has nothing informative to retrieve. Reaching it took four measurement corrections -- three inflating the apparent benefit, the fourth making an effect that size look resolvable -- none visible in the results table. We give the conditions an agent-memory ablation must satisfy and detection procedures that need no knowledge of the specific defect.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07782
PDF
-
Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models
2026-10-06 05:09:02Ziyuan Yang, Wenxuan Ding, Shangbin Feng, Yulia TsvetkovAbstract
Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs become increasingly common, recent work has explored various safety interventions, including prompting, supervised fine-tuning, and routing-based expert steering. However, these methods show inconsistent improvements across models and evaluation distributions, and the intervention into model behavior or internal states introduce safety-utility tradeoffs by over-refusal. Rather than manipulating internal states to steer model behavior, we instead ask whether routing states can serve as diagnostic signals for multimodal safety. We find that router logits indeed provide highly predictive signals of whether a multimodal input is safe or not. Motivated by this observation, we introduce a lightweight router-logit safety detector that reads out routing signals during prompt prefill and identifies unsafe requests before generation, without modifying model parameters or expert routing. Across Qwen3-VL and Kimi-VL, the proposed detector substantially reduces safety errors on the HoliSafe benchmark and resoundingly generalizes to out-of-distribution safety benchmarks featuring different safety patterns, including MISHard and MM-SafetyBench. The success of the proposed router-logit detector also suggests a broader perspective on model internals: rather than focusing only on manipulating internal components to steer behavior, simply reading naturally emerging signals and linking them to an external safety mechanism can provide a simple, effective, and non-intrusive complement to existing safety interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07774
PDF
-
What Frame-Level Labels Can and Cannot Do for Small-UAV Point Detection in Thermal Video
2026-10-06 03:58:26Wonbin Son, Gyumum Choi, Junil Seo, Hyungjoon KimAbstract
The growing use of unmanned aerial vehicles (UAVs) has increased the importance of image-based UAV detection. Learning-based detectors are trained on imagery and annotations, with annotation type determining the information available during training. We focus on learning localization from frame-level target presence/absence labels when sensor or scene changes make spatial annotations for additional training burdensome. We analyze the detection capability, learning behavior, and potential applications of an existing architecture for point detection of small UAVs, trained with presence/absence labels and requiring no external detector. The architecture freezes spatial features learned through classification and trains a readout with the same frame labels to produce spatial score maps and point detections. On two thermal infrared datasets, CST Anti-UAV and Anti-UAV410, we evaluate localization hit rates and detection rates under false-alarm constraints, analyze the effects of training stages, label allocation, synthesis, and model configuration, and compare with bounding-box detectors. We also explore potential applications on Airborne Object Tracking (AOT) using its visible-light imagery and frame labels. Classification training strengthened target-related spatial responses, while readout training helped extract them consistently. Distributing similar label counts across more videos yielded higher localization hit rates, while synthesis effects varied by dataset and evaluation criterion. Higher localization hit rates did not always improve detection under false-alarm constraints, and failures remained when target signals were weak relative to background variation and under cross-dataset transfer. These findings provide guidance on label allocation, spatial representations and readouts, synthesis, and false-alarm control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07705
PDF
-
Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation
2026-10-06 03:45:12Thanh Dong, An Ngo, Minh Dau, Rajesh KumarAbstract
We study the robustness of keystroke dynamics for detecting large language model (LLM)-assisted writing. We introduce a Vietnamese keystroke dataset capturing realistic writing modes, including bona fide composition, transcription, and paraphrasing. We also define a behaviorally grounded threat model in which users deliberately alter typing patterns. To implement the threat model, we create behaviorally manipulated variants of the data designed to evade keystroke-based detection. We evaluate four keystroke modeling approaches: temporal and rhythmic representations, and sequential representations modeled with a one-dimensional convolutional neural network (1D-CNN) and TypeNet, under user-independent and context-independent settings. The results show that sequential models outperform feature-based approaches in most cases and that keystroke signals encode discriminative information about the writing process. However, detection is not uniformly robust: transcription is reliably identified, while paraphrasing and adversarially manipulated samples are frequently misclassified as bona fide when not explicitly modeled. To address this, we incorporate adversarial training using behaviorally manipulated data, which substantially improves separability and robustness. These results suggest that keystroke-based detection depends critically on exposure to diverse writing behaviors, and that strong performance under limited conditions does not generalize to realistic or adversarial settings without targeted modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07700
PDF
-
Evaluating human-AI workflows for field research in viticulture
2026-10-06 03:04:47Niko Carvajal Janke, Daoyuan Jin, Shivranjani Baruah, Nicholas Gunner, Jacob Maus, Yu Jiang, Kaitlin M. GoldAbstract
We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 2021-2024 commercial scouting records and remote-sensing measurements across 140 hectares could support 2025 red-leaf symptom forecasting for prioritized scouting and virus testing. In Workflow 1, Aleks v1, a multi-agent research system, developed forecasting models with iterative human refinement. We applied Aleks's 2024 vine-scale model to updated 2025 predictors and evaluated red-leaf forecasts against independent 2025 scouting. In retrospective simulations surveying 45% of all vine positions, adding model-informed row prioritization to adaptive scouting increased the encountered proportion of newly recorded red-leaf observations from 85.8% to 94.1%. Within-block scouting comparisons suggested the model mainly improved scouting allocation among blocks. Despite unreliable internal 2024 performance estimates from synthetic oversampling before train/test splitting, Aleks developed an informative vine-scale model in 145 minutes, increasing throughput and answering our research questions. In Workflow 2, we assessed whether higher model-score vines had more frequent virus detection, and whether Aleks could infer this sampling goal from a general prompt with data and literature. Aleks's plan prioritized balanced vineyard and model score coverage, while our plan prioritized field efficiency and high-model-score oversampling. Aleks's and our plans yielded 41/50 (82%) and 97/100 (97%) sampled vines. Aleks's plan omitted instructions for replacing missing vines, limiting implementation and operational value. Five of 137 sampled vines tested positive for grapevine red blotch virus (model score ROC AUC 0.735). These findings support assessing AI interactions by how well they advance field research objectives under live, project-specific constraints.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07669
PDF
-
Fine-Tuning VLM for Enhancing AI's Spatial Intelligence: Understanding 3D and 2D Rotations
2026-10-06 02:46:30Uttamasha Monjoree, Wei YanAbstract
Spatial intelligence is a fundamental skill in multiple domains, such as Science, Technology, Engineering, and Mathematics (STEM), Medicine, Architecture, and Construction. Recent studies indicate that Vision-Language Models (VLMs) still face limitations in spatial reasoning, which inhibits artificial intelligence (AI) from performing practical spatial tasks. Using multiple object-rotation datasets developed for training and evaluation, our experiments demonstrated promising improvements in both 2D and 3D rotation detection. Fine-tuned Google DeepMind-built Gemma-4 mixture-of-experts (MoE) models significantly outperformed fine-tuned Gemma-4 generalist models in predicting rotations defined by both their axes and angles. Fine-tuning also substantially improved angle estimation for 2D representation without requiring an explicit coordinate system. Furthermore, identifiable objects did not improve angle-detection accuracy; instead, objects with prominent linear features showed improved performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.04206
PDF
-
A Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss Optimization
2026-10-06 02:18:10Tien-Hong Lo, Fong-Chun Tsai, Ting-An Hung, Yu-Hsuan Hsieh, Yao-Ting Sung, Berlin ChenAbstract
Prosodic stress is a crucial aspect of automatic pronunciation assessment (APA), encompassing both sentence stress detection (SSD) and word stress detection (WSD). SSD highlights semantically salient words that shape discourse meaning, while WSD identifies the primary stressed syllable within each word to ensure lexical clarity. However, most prior work treats SSD and WSD as independent tasks, overlooking their shared reliance on prosodic cues such as pitch, duration, and intensity. To address this gap, we propose an effective SSD approach combining SSD with auxiliary WSD via a novel modeling paradigm. In addition, we introduce a word-span stress regularizer (WSR) that concentrates token-level SSD probabilities within each stressed word span. Experiments on the TinyStress-15K benchmark show that the proposed method outperforms strong baselines, with the complete configuration achieving the best SSD result.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07626
PDF
-
Modeling Latent Disturbances for Robust Decision-Making in World Models
2026-10-06 01:38:38Junwon Seo, Andrea BajcsyAbstract
In this paper, we study robust decision-making in the latent space of world models (WMs). Robust optimization is a mathematical framework where, given explicitly specified dynamics and physically meaningful disturbances, a robot can select actions that remain effective even under worst-case disturbances. However, applying this principle to the learned latent space of WMs introduces a fundamental challenge: because WMs have fully learned state spaces and dynamics inferred from high-dimensional observations, it is unclear how to define latent-space disturbances that faithfully represent uncertainty in the underlying system. Our key idea is to model a latent-space disturbance as a perturbation to the learned latent dynamics that induces pessimistic but plausible transitions. Specifically, we construct a set of plausible latent dynamics by combining a dynamics-aware similarity metric that captures plausible transitions with out-of-distribution detection that excludes implausible latent states. We calibrate this uncertainty set over latent dynamics using conformal prediction, ensuring that WM imaginations induced by the latent disturbance remain plausible without becoming overly pessimistic. We then jointly optimize robust robot actions and the worst-case latent disturbances through game-theoretic optimization. We leverage this latent-space robust optimization to robustify policy steering, considering two paradigms: latent safety filtering and sample-and-verify steering of a generative control policy. Our controlled simulation experiments show that our latent disturbance enables robust decision-making directly in WM latent spaces, and hardware experiments with a Franka manipulator show that modeling latent disturbances enables robust policy steering, reducing failures by 70% in safety filtering and 54% in sampling-based policy steering. Project website: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07599
PDF
-
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
2026-10-06 00:42:45Hang He, Li Wang, Hao Chen, Yuchen Shao, Yuling Shi, Lisheng Wang, Peiyang Liu, Goose Lin, Zaiyuan Wang, Haiying Sun, Ting Su, Chengcheng WanAbstract
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection and rarely assess whether an agent can develop a working checker in a repository from start to finish. We introduce CheckerBench, an executable benchmark of 300 tasks derived from 297 CVEs across 167 repositories, 85 CWEs, and five language ecosystems. Each task includes vulnerable and fixed revisions, a pinned analysis environment, and a checker scaffold. We further introduce CheckerLab, a common evaluation framework that independently rebuilds submitted checkers and measures vulnerable-fixed diagnostic contrast, patch localization, false positives, and tool use. Across 21 model-harness configurations and three independent repeats per configuration, mean Pass@1 is 32.30%, while the best reaches 45.33%. These results show that reliable, reusable checker development remains challenging for current coding agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07557
PDF
-
When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability
2026-10-05 21:40:07Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar, Rahim TafazolliAbstract
When does a second artificial intelligence (AI) component improve a primary network-fraud decision rather than add operational burden? We study this question through a role-aware Decider-Supervisor (DS) framework with blockchain auditability, evaluating four directional configurations that combine centralised machine learning, a Federated Averaging (FedAvg)-trained federated meta-model, and Base or Quantized Low-Rank Adaptation (QLoRA) large language model variants. The analysis compares primary-only and supervised decisions using non-hard fraud performance, intervention burden, conditional calibration, traffic-mix and Review-capacity sensitivity, dependability tests, and blockchain lifecycle controls. The deterministic hard gate resolves 89.994% of fraudulent requests, leaving the non-hard population as the main AI decision setting. Conditional validation calibration does not produce a consistently transferable supervisory advantage on deployment replay. DS-3 QLoRA is the least disruptive supervised configuration, but it still underperforms its primary FedAvg stage in F1 and total errors. Across 36 reweighted traffic mixtures, supervision reduces total errors only for DS-4 Base in two extreme high-fraud scenarios. Blockchain tests support digest verification, tamper detection, authorisation, single-use review resolution, and post-finalisation integrity, while exposing a pre-finalisation single-write limitation. The results show that the value of AI supervision depends on role assignment, calibration, escalation policy, traffic composition, and lifecycle controls rather than on the presence of a second model alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07434
PDF
-
Entropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent Communication
Abstract
We study decentralized multi-agent target search where homogeneous agents communicate intermittently at Poisson-distributed times. Standard unconditional belief fusion wastes communication opportunities by synchronizing agents during high-entropy exploration, when diverse independent beliefs provide better coverage than a premature consensus. We introduce \emph{entropy-gated belief coordination}, in which agents skip fusion while their collective entropy ratio exceeds a threshold~\(\theta\) and merge only during exploitation, consistent with the bifurcation structure of nonlinear opinion dynamics and the submodular structure of the per-step information gain objective. We further derive \(\Istep(\alpha,\beta)\), the expected mutual information per observation step between two agents' binary sensors, as an interpretable, communication-free measure of sensor informativeness that motivates the gating design and guides system-level analysis. Experiments across 103{,}680 trials (nine grid sizes up to \(100{\times}100\), Poisson communication timing, four target movement patterns) show that the Entropy-Gated Trust-Decay Planner (\textsc{EG-TDP}), which adds a detection-probability planner switch in exploitation mode, achieves mean belief quality \(\bar{Q}=0.300\) (mean belief mass at the true target cell, averaged across all trials and steps), a \(58.9\%\) gain over arithmetic mean and a \(37.4\%\) gain over visit-weighted fusion. On representative configurations, EG-TDP also outperforms a joint-Bayesian reference that uses all agents'~observations at every step, despite operating under random intermittent contact only.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07432
PDF
-
Inference and learning in sparse autoencoders as natural gradient flow
2026-10-05 21:03:21Hadi Vafaii, Tejas Rao, David Chanin, Thomas Fel, Jacob L. Yates, Bruno Olshausen, David Klindt, Dileep George, Miguel L\'azaro-GredillaAbstract
Sparse autoencoders are widely used to uncover interpretable features in neural networks, yet reliable recovery remains difficult when features overlap or activate infrequently. These challenges involve both inferring which features explain an input and learning the dictionary that represents them. Here, we unify inference and dictionary learning as natural-gradient flows on a shared variational free energy. We instantiate this framework as BeFOND, an encoder-free sparse coding model with closed-form inference and learning dynamics. We show how recurrent explaining away reduces interference between overlapping features, while Fisher preconditioning can compensate for the slow learning of rare features. On synthetic data, BeFOND improves dictionary recovery and rare-feature detection, with a growing advantage over amortized baselines as superposition increases. On language-model activations, it improves single-feature concept detection and selective intervention, outperforming pretrained reference SAEs with substantially less training data. Its feature quality continues to improve with dictionary width, whereas the evaluated baselines largely plateau. Together, these results show how improving inference and learning within a unified probabilistic framework can make better use of data and dictionary capacity to interpret and intervene on neural representations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07389
PDF
-
Who Wrote It Is Not Enough: Detecting Who Contributed the Insight
2026-10-05 20:34:03Zhuoyang Zou, Abolfazl Ansari, Jiaxi Yang, Delvin Ce Zhang, Qian Chen, Dongwon Lee, Wenpeng YinAbstract
As LLMs increasingly assist scientific writing and peer review, detecting who wrote the text is no longer sufficient: we need to determine who contributed the underlying insight. We introduce Insight Provenance, the task of identifying whether a review insight originates from a human, an LLM, or their hybrid contribution. We construct InsightProv-v0 from 4,057 scientific papers and 12,660 human reviews, simulating different levels of LLM involvement with GPT-4o, Gemini, and DeepSeek and annotating provenance at the sentence level. We show that strong performance on raw data can be misleading, as models exploit linguistic and textual-authorship shortcuts that degrade substantially under progressively debiased evaluation. We therefore propose a two-stage adversarial framework that suppresses shortcut signals while preserving provenance-relevant information. Beyond detection, extensive analyses reveal what makes intellectual authorship identifiable: paper grounding and neighboring review context provide complementary provenance signals, while human, hybrid, and AI insights systematically differ in their information sources and failure modes. Most strikingly, AI insights predominantly remain close to generic or paper-provided information, whereas human insights more often introduce external knowledge and independent judgment. These findings suggest that while wording can be rewritten by an LLM, the provenance of an idea leaves a deeper and more persistent signal.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07365
PDF
-
Localize Any Object in X-Ray Security Scans without Human Annotation
2026-10-05 19:57:49Yaqi Cai, Mingxuan Liu, Lorenzo Vaquero, Ning Wang, Nan Pu, Feng Xue, Elisa Ricci, Nicu SebeAbstract
Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyday RGB images that dominate web-scale visual data, X-ray scans exhibit distinct color patterns, ambiguous boundaries, and compositional structures caused by volumetric superposition. These gaps hinder the direct zero-shot transfer of dense perception foundation models trained on web-scale RGB data. Moreover, annotated X-ray data is scarce and requires expert labeling, limiting both the training of generalizable X-ray native models and the adaptation of RGB foundation models for X-ray data via fine-tuning. Given these challenges, the bright promise of highly generalizable perception models, enabled by data scaling laws in the RGB domain, remains largely out of reach for X-ray inspection. To this end, we introduce LAO-X, a self-supervised adaptation framework that Locates Any Object in X-ray scans using diverse synthesized image--annotation pairs with granularity-aware supervision. LAO-X first designs a saliency-guided X-ray object mining module to separate diverse object instances, which are then used for physics-guided synthesis in the absorbance domain. LAO-X further incorporates an occlusion-controlled curriculum strategy to fine-tune a Segment Anything Model 2 (SAM2) localizer, progressively adapting it to X-ray scans with increasing object counts and overlap levels. Experiments on six X-ray benchmarks show that LAO-X substantially improves category-agnostic localization, achieving 2\% to 23\% mAP gains over SAM2 and X-ray specific baselines in heavily cluttered scenarios, entirely without human-annotated labels.
Abstract (translated)
URL
https://arxiv.org/abs/2610.07326
PDF
