Language_Model
-
Evaluating Language Model Features for Zero-Shot Time-Series Anomaly Detection Under Isolation Assumption
2026-11-05 09:37:57Romain Hermary, Nesryne Mejri, Djamila AouadaAbstract
Time-Series Anomaly Detection (TSAD) is a fundamentally challenging task: it is unsupervised, requires high local precision capabilities, and suffers from limited labelled data. Recent work has explored adapting Large Language Models (LLMs) to time-series via cross-modal transfer. However, existing approaches are poorly suited to Multivariate TSAD (MTSAD), as tokenisation often obscures fine-grained temporal and variables structures, and most methods optimise auxiliary objectives such as forecasting or reconstruction. We posit that these surrogate objectives become unreliable as model capacity increases. Highly expressive models risk reconstructing or forecasting anomalies, undermining the foundations of both strategies. Instead, we propose to use LLMs purely as feature extractors and directly analyse their induced feature spaces. In this work, investigate the ability of LLMs to provide useful representations for MTSADs in a zero-shot setting through classification. To this end, we study the separability of the extracted features, under the assumption that anomalous features should be isolated from normal ones. We analyse their temporal and contextual discriminative ability using simple step-wise tokenisation schemes, with one time-step per token, which preserve fine-grained local information. Their usability for MTSAD is assessed using an unsupervised Isolation Forest, enabling a direct evaluation of the resulting representation quality. We further investigate whether the observed performance can be attributed to the language-related pre-training of the LLMs or arises independently of it. Our results provide empirical insight into the ability of LLMs to represent multivariate time-series for anomaly detection and highlight broader applications of cross-modal foundation models.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07720
PDF
-
CAMP: Context-Aware Mapping and Placement for LLMs on 3D-IMC Arrays
2026-11-05 09:27:31Orhun G\"orkem, Athanasios Vasilopoulos, Georgios Pagonis, Victoria Clerico, Hadjer Benmeziane, Irem Boybat, Hsinyu Tsai, Abu Sebastian, William Andrew SimonAbstract
Large Language Models (LLMs) incur severe memory-access overheads due to the cost of loading large weight matrices and key-value (KV) caches. Analog In-Memory Computing (AIMC) is an emerging solution that enables computation directly on static weights stored in memory, substantially reducing energy and latency. 3D-IMC further stacks memory arrays into vertical tiers, increasing capacity but revealing a new challenge: how weights are placed in memory determines which matrix-vector multiplications (MVMs) can execute concurrently, affecting latency and throughput. The concurrency aspect of 3D-IMC weight-mapping remains underexplored in the literature, leading to sub-optimal utilization of compute resources on 3D-IMC chips. In this context we propose CAMP (Context-Aware Mapping and Placement), an inference-context-aware weight mapping algorithm for 3D-IMC-based LLM accelerators. CAMP captures the potential resource contention resulting from the architecture, targeted network, and runtime context in a conflict matrix, enabling throughput-optimized weight mapping. This mapping is refined through a profiling-driven feedback loop that efficiently prunes the search space and returns optimized mappings within practical runtimes. CAMP is an offline, software-based solution requiring no hardware changes and improving 3D-IMC compute utilization from 42.4% to 60.3%, delivering up to 2.0x higher 3D-IMC throughput and 1.74x higher end-to-end throughput over state-of-the-art mapping algorithms.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07707
PDF
-
MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
2026-11-05 09:14:26Yizhen Jiang, Haowei Guo, Tianyi Bai, Zengjie Hu, Lu Ma, Zhengyang Zhao, Haoze Sun, Peng Pei, Wentao ZhangAbstract
Large language model agents are increasingly deployed through the Model Context Protocol (MCP), which allows them to discover and invoke tools across multiple servers at runtime. Existing MCP benchmarks primarily measure task completion; where they diagnose failures, they do so after execution rather than building specific reasoning, execution, and memory failure risks into task construction. We introduce MCPHallu, a benchmark for diagnosing hallucination-prone agent failures in MCP environments along three axes: reasoning, execution, and memory. MCPHallu contains 358 tasks across five capability domains and runs on 36 production MCP servers in isolated containers. Each task is designed with a structural trigger that makes one of four subtypes the dominant failure risk: Branch Collapse, Unreachable Goal, Tool Misuse, or Context Forgetting. This design enables subtype-level analysis rather than aggregate task success alone. We evaluate fourteen frontier LLM agents from eight vendors on 5{,}012 trajectories. Current MCP agents remain vulnerable to hallucination-inducing tool environments, achieving an average score of 0.642 on a $[0,1]$ scale (higher is better). Failures concentrate on Unreachable Goal tasks, where the average score drops to 0.458 and 23.2\% of runs pass, indicating that agents often continue issuing tool calls or claim successful completion rather than recognizing infeasible goals. Subtype rankings diverge sharply: a model's rank shifts by 6.9 of 13 positions on average across subtypes, and Branch Collapse is uncorrelated with Unreachable Goal across models ($r = -0.12$). MCPHallu is released at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07689
PDF
-
Egocentric Action Recognition with Objects and Vision-Language Affordances
2026-11-05 09:02:25Ra\'ul Boix-Aldeguer, Manuel Benavent-Lledo, David Ortiz-Perez, Jose Garcia-RodriguezAbstract
Action recognition, and more specifically egocentric action recognition, is a core task in computer vision, with applications such as monitoring the daily life activities of elderly people and task assistance. Recent methods rely on visual modalities such as RGB video or depth. However, in egocentric video, an action is largely defined by its objects, which these methods rarely model. We propose a method that combines a frozen SlowFast video expert with an attention-based object expert by late fusion. Each object is represented with its affordances, that is, what can be done with it, generated zero-shot by a vision-language model. Since datasets such as MECCANO annotate only the objects involved in each action, evaluating with these boxes tells the model which objects are active. We therefore train on annotated boxes and evaluate the method with detections from the official active-object detector, and with annotated boxes as an upper bound. Without affordances, our fusion reaches 68.4% Top-1 with annotated boxes but 49.0% with detections. About half of this drop comes from non-active detections. To remove them, the same vision-language model generates an interaction affordance that decides whether a hand is manipulating each detected object. On MECCANO, objects raise the Top-1 of the video expert from 44.9% to 49.0%, and the two affordances raise it to 49.9%, above SlowFast and object-aware RGB baselines. Code will be released upon acceptance.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07673
PDF
-
English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models
Abstract
Expert pruning compresses Mixture-of-Experts (MoE) language models by removing the experts that a calibration set marks as unimportant. Studies of high-resource languages largely find that English calibration transfers well to other languages. We test this for Lithuanian: we pruned four MoE models with REAP, removing 25% or 50% of the experts with English, Lithuanian or mixed calibration, and evaluated both languages on reading comprehension, translation and language modelling. English calibration does not transfer to Lithuanian: at 25% pruning, English comprehension fell by a median of 1.7 points but Lithuanian by 21.4. The transfer is asymmetric. Lithuanian calibration removed most of the Lithuanian loss and never significantly hurt English comprehension, which was on average 2.5 points better than under English calibration; only English language modeling got slightly worse. Routing suggests why: in the last layers, Lithuanian sends 55-72% of its expert selections to just eight experts, against 19-39% for English, and English calibration removes some of these experts. Compressed models should be calibrated, and evaluated, in every language they must serve.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07654
PDF
-
Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems
2026-11-05 08:38:51Vladimiros Peilivanidis (ARPA Hellenic Logical Systems)Abstract
Current autonomous logical systems rely on a fragile assumption: that language models should dynamically write code, guess API payloads, and memorize operational constraints through prompt engineering. In practice, this burns massive context windows, inflates API bills, and produces brittle agents that fail unpredictably in production. In this work, we present Skillware, an open architectural framework and capability registry that formally separates what an agent wants to do from how that task is executed. Instead of prompting models with loose text instructions or markdown files baptized as 'skills', Skillware equips them with modular, versioned software capability bundles. Much like skill hotkeys in video games that execute deterministically under fixed world rules, each bundle combines a typed JSON input contract, deterministic Python code, task directives, bundled datasets, and automated unit tests. In-process adapters translate these capabilities into native tool declarations for any model, from frontier cloud APIs to local open-weight runtimes with zero network latency. Evaluating 23 frontier and open-weight models across 368 benchmark conditions, we show that small local models (3B to 8B parameters) equipped with Skillware consistently outperform unequipped frontier models on complex multi-step workflows. They cut token usage by up to 84.8%, slash inference costs by up to 97.3%, and eliminate parameter errors entirely. True agent reliability does not come from larger models or longer prompts, but from equipping logical systems with verified, deterministic software. Finally, we articulate the trajectory of capability bundles across an invariant continuum of information processing systems: from digital logical systems today, to IoT, drones, and embodied robotics tomorrow, establishing a foundation for auditable, real-time capability execution.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07652
PDF
-
What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays
2026-11-05 08:35:38Xiaodong Wu, Zhimin Zhao, Qi Li, Chaklam Cheong, Xiangman Li, Jianbing NiAbstract
Third-party application programming interface (API) relays offer access to large language models (LLMs), often at lower prices. Users depend on these services for model quality, instruction compliance, and accurate billing. However, existing studies leave unclear whether relays meet these expectations together. We test 20 relays offering GPT-6 Astra and Claude Opus 5. First, we compare answers to knowledge questions with batch-matched official responses. In our first-round sample, the analysis flags 7/10 low-price and 2/10 same- or higher-price relays for behavioral differences. On retesting 35 pairs, seven gain or lose a flag under the original rules, and six under matched correction families. Because answer comparisons cannot reveal every delivery problem, we examine returned content and tool permissions. No injection is confirmed in 3,332 screened responses to a fixed, non-adversarial code and setup workload, yet four relays return tool calls despite instructions disabling them in the first round. Finally, to connect reported usage to actual costs, we compare input-token counts with official references and check balances. For identical requests, five relays report 4,200 to 60,000 more input tokens than the official API. Where balances are available (six services), charges follow reported usage at listed prices, including extra reported input tokens at one service. Our study shows that advertised models and prices are insufficient to judge relay reliability. It identifies unexplained billed token quantities and tool-permission violations as risks and shows why service evaluations need repeated measurements.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07650
PDF
-
Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs
2026-11-05 08:18:36Sai Yashwant, Manoj Kumar Gondimalla, Arjun Sharma, ShubhamAbstract
Many enterprise projects now pass free text to large language models (LLMs), and that text often contains personally identifiable information (PII) such as names, phone numbers, email addresses, home addresses and dates of birth. Once a prompt is sent, this data is copied into provider systems, application logs and observability traces. Redacting PII before the call is an obvious control, yet teams seldom have numbers on what it costs in latency or what it lets through. This paper compares four redaction designs that any LLM pipeline can adopt: a pure regular-expression (regex) redactor, Microsoft Presidio running on a spaCy model, a hybrid in which Presidio finds only person names while regex handles structured identifiers, and a fast hybrid that calls spaCy's named-entity component directly. All four share a known-entity rule, which removes the person the system already knows it is handling, and a consistent placeholder scheme, so the LLM can still tell one person from another after redaction. We evaluate the designs on a sample workflow, which we call ProfileAssist, that turns resumes into structured profiles, using 100 synthetic resumes (523 characters on average, with 900 PII values and 600 business terms that must survive). Regex ran at a 0.20 ms median but caught only 88.9% of PII, because it cannot find names that are not known in advance, such as the references listed in a resume. Presidio, hybrid and fast hybrid each caught 100% of PII and kept 100% of business terms, at median latencies of 37.59 ms, 30.23 ms and 13.48 ms. Measured against a 9,120 ms median LLM call, even the slowest option adds only 0.41% to the request. We therefore recommend the fast hybrid as a default for LLM pipelines that handle personal data, with regex kept as a safety net rather than as the only control.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07633
PDF
-
Embedding-Space Fingerprinting of LoRA Fine-Tunes: Recovering the Training-Data Domain from the Model Artifact Alone
Abstract
When a base language model is fine-tuned with Low-Rank Adaptation (LoRA), how much of the training data domain leaks into the resulting artifact? This paper studies whether a simple classifier can recover the domain of a fine-tune given only the model artifact (weight deltas, internal activations on a fixed probe set, or generated text) without ever observing the training data. Using one base model (Qwen3.5-0.8B), 36 LoRA fine-tunes are produced over 18 public datasets in five domains (medical, code, mathematics, non-English text, narrative prose), and three feature families are extracted at decreasing levels of access: white-box weights, gray-box activations, and black-box outputs. A leave-one-dataset-out (LODO) protocol, frozen before any result was seen, tests whether the domain of a fine-tune trained on a previously unseen dataset can be identified. The domain is recoverable well above chance (20%) from gray-box activations (61%) and black-box outputs (64%); white-box weight statistics reach 42%. Contrary to the pre-registered hypothesis that signal decays monotonically from weights to activations to outputs, activations and outputs were more informative than the weight-delta statistics. The black-box result holds unchanged (64%) when only generated text is used, without token probabilities. Domain accuracy is also stable when a third run per dataset is trained on an independently drawn data subsample, and black-box predictions are unaffected by the LoRA rank (8-64). All code and per-run feature vectors are released.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07610
PDF
-
Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks
2026-11-05 07:46:29Pengpeng Qiao, Yang Cao, Lingling Zhang, Guo Cheng, Junwei Chen, Manjiang Yu, Wei Yang Bryan Lim, Masatoshi YoshikawaAbstract
Federated fine-tuning of large language models (LLMs) under heterogeneous client capacities is increasingly important, and low-rank adaptation (LoRA) with heterogeneous ranks makes it practical. Existing server-side aggregators compose local matrix updates $\Delta W_i$ from client-specific LoRA factors $(A_i,B_i)$ before aggregating them. Although these matrix updates lie in the same weight space $\mathbb{R}^{m\times n}$ and can be averaged directly, the LoRA factors that generate them may expressed client-specific local basis. In the typical compose--aggregate--factorize--dispatch loop, this basis inconsistency can make the rank-$r_i$ reference prefix dispatched to lower-rank clients unstable after server-side refactorization. In this work, we propose \textbf{FedAbA}, a basis-consistent federated LoRA aggregation framework for heterogeneous ranks. FedAbA first extracts each client's local basis, aligns it to the corresponding prefix of the global reference basis, and constructs a basis-consistent reconstruction of each local matrix update before aggregation. It then aggregates these reconstructions with weights that combine client data size and consistency score, followed by exact coefficient-space SVD refactorization and gauge fixing before rank-prefix dispatch. Our theoretical analysis clarifies the role of basis consistency and supports the proposed consistency-aware aggregation mechanism. Extensive experiments show that FedAbA outperforms representative federated LoRA baselines, with the largest gains under the strongest rank heterogeneity.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07598
PDF
-
TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs
2026-11-05 07:43:29Chongyu Qu, Ritchie Zhao, Yufan He, Dong Yang, Zhengyi Lu, Junchao Zhu, Tianyuan Yao, Juming Xiong, Junlin Guo, Yanfan Zhu, Yuechen Yang, Daguang Xu, Bennett Allan Landman, Yucheng Tang, Yuankai HuoAbstract
Vision-language models (VLMs) applied to 3D medical scans face a structural memory wall. A single CT or MRI volume produces tens of thousands of vision tokens, and the resulting key-value (KV) cache scales linearly with both batch and context. Existing KV compression methods operate on the cache's feature or token statistics, or apply 1D and 2D transforms, leaving the three-axis spatial structure in the cache unexploited. We propose TACT-KV (Tri-Axis Cosine Transform), a calibration-free KV compression method that exploits strong spatial correlations in visual KV states along all three anatomical axes of 3D scans. This correlation concentrates the KV cache energy under a frequency-domain transform. TACT-KV applies a separable 3D discrete cosine transform to the KV cache, allocates a per-layer bit budget across frequency bins via reverse water-filling (more bits to high-energy components), and quantizes each bin with a fixed scalar codebook. We derive a close-form relation: the distortion reduction from adaptive bit allocation is dominated by the spectral concentration of the transformed cache. Across six medical VLMs and two 3D CT benchmarks, TACT-KV achieves the lowest 1-bit prediction-flip rate on eleven of twelve model and dataset pairs in our main comparison. The same advantage reproduces on four general-purpose VLMs evaluated on video tasks, indicating that the benefit of exploiting three-axis structure generalizes beyond medical imaging. At equal high-bandwidth memory (HBM), TACT-KV scales the decoding batch size on a single GPU by up to $8\times$.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07593
PDF
-
SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking
2026-11-05 07:04:45Moonseok Choi, Jongwon Jeong, Minki Kang, Giung Nam, Juho LeeAbstract
Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time. Whereas existing compression methods target unconstrained generation, we first identify a fundamental mismatch: under structured generation, grammar constraints reduce the model's output distribution to valid tokens, and the logits matter most at the small set of positions that decide the agent's action. Motivated by this finding, we propose SKIM (Selective Knowledge-Informed Masking), the first pruning and distillation framework for LLM agents under structured generation, with both stages guided by token role. SKIM partitions token positions into context, decision, and format categories, and this partition drives two complementary axes: (1) category-aware pruning saliency scores that preserve parameters most relevant for decision positions; and (2) an on-policy distillation objective that aligns student and teacher on valid tokens, paired with category-aware feature matching. We evaluate SKIM on tool-calling benchmarks and within multi-step agent loops, across multiple model scales and sparsity levels. SKIM consistently improves accuracy over baselines, with its superiority becoming most striking in high-sparsity regimes where conventional methods struggle, demonstrating the potential of category-aware compression for deployment-time grammar-constrained agents.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07558
PDF
-
OptIMerge: Optimization-Based Merging of Diffusion Models
2026-11-05 06:50:09Viraj Shah, Ashwini Pokle, Peyman Milanfar, Mauricio Delbracio, Hossein TalebiAbstract
The arithmetic merging of weights from multiple task-specific models fine-tuned from a shared base model, commonly known as model souping, has emerged as a popular strategy for multi-task learning without the computational overhead of joint retraining. However, naive scalar weight averaging frequently leads to severe performance degradation when the constituent models learn structurally divergent feature representations, leading to destructive parameter interference. We study this problem in a largely unexplored setting: merging image-to-image (I2I) diffusion models fine-tuned for dense, pixel-accurate tasks such as image restoration. Unlike the large language models (LLMs) and text-to-image (T2I) diffusion models for which most merging methods were developed, I2I experts encode conflicting spatial priors (e.g., anisotropic motion-blur vs. isotropic defocus-blur) in their convolutional filters, where both naive soup and LLM-style element-wise merging introduce visible artifacts. We introduce OptIMerge, a gradient-based optimization framework: instead of relying on heuristic scalars, OptIMerge learns highly expressive, yet parameter-efficient merger coefficients by minimizing a multi-task diffusion loss over a small set of 100-500 images. OptIMerge parameterizes the merge with architecture-aware transformations: for attention layers, a structured low-rank feature alignment with explicit channel biases; for convolutional layers, per-kernel merger coefficients, and a low-rank Cayley transform that aligns channels by orthogonal rotation without distorting the filters. By keeping the experts frozen and optimizing only these lightweight merger parameters (equivalent to <0.4% of the network footprint), OptIMerge achieves simultaneous multi-task capabilities that rival computationally expensive joint training and decisively outperform zero-shot model soups.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07543
PDF
-
FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving
2026-11-05 06:50:05Xuan Wang, Zhuanhao Wu, Tingzhu Fang, Xushi Li, Sicheng Zhang, Zhenyu Yang, Feng Liu, Zhaohui Fan, Qiang Xie, Huayi Zou, Yuncong Liu, Zeyu Song, Ke Zhu, Yanjia Zeng, Jingchun Gao, Yan Shi, Kui Luo, Gezi Li, Liangjun Feng, Cheng LiAbstract
In large language model (LLM) serving systems, the key-value (KV) cache grows linearly with sequence length and concurrency, so long-context inference easily hits the high-bandwidth memory (HBM) capacity wall and results in low concurrency. Offloading the KV cache to host dynamic random-access memory (DRAM) frees HBM space and raises concurrency, but the additional cache management and host-to-device (H2D) load overhead inflates inference latency, higher concurrency fails to translate into effective throughput. We present FlashOffloading, a host-DRAM-centric inference architecture that fully offloads the KV cache in both the prefill and decode phases. FlashOffloading builds rolling HBM cache for prefill, a hot cache for decode, a reverse sparse index with zero extra miss-lookup overhead, and a compute--load overlapped kernel, optimizing KV offloading latency across the entire pipeline and delivering throughput gains under a time-per-output-token (TPOT) service-level objective (SLO). In experiments deploying GLM-5.2 with multi-token prediction (MTP3) speculative decoding on an Ascend910C prefill--decode (PD)-disaggregated platform, FlashOffloading improves prefill throughput by up to 1.38\(\times\) and decode throughput by up to 1.91\(\times\) under a 30 ms TPOT constraint. FlashOffloading is integrated into an open-source serving framework: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07542
PDF
-
CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal Transition On-Policy Self-Distillation
2026-11-05 06:49:51Ying Li, Yongle Cheng, Jing Li, Xingquan Cai, Yawei LuoAbstract
Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet existing benchmarks mainly focus on static scene understanding. When objects are moved or swapped, models must infer not only spatial relations but also how interventions change the scene state. To address this problem, we introduce CST-Bench, a benchmark for counterfactual spatial reasoning. CST-Bench contains 7,082 examples covering 6 intervention types and 12 transformation operators, with dense causal annotations including intervention sources, affected relations, expected effects, invariant relations, and metric changes. We benchmark general-purpose MLLMs on CST-Bench and further compare post-training strategies on CST-Bench and standard spatial benchmarks. Results show that methods effective for ordinary spatial reasoning can still fail under counterfactual interventions. We further formulate counterfactual spatial reasoning as causal state-transition modeling and propose CT-OPSD, which uses CST-Bench annotations to guide a teacher model in learning counterfactual state transitions and causal reasoning chains. These chains are then distilled into a student model that reasons only from real observations. Overall, experiment results establish CST-Bench as a challenging benchmark and reusable supervision resource for counterfactual spatial reasoning. CT-OPSD further provides an initial demonstration of how its annotations can support model improvement.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07541
PDF
-
Action-Conditioned VLM Monitoring for Autonomous Vehicle Semantic Anomalies
2026-11-05 06:48:39Daniel Adejumo, Omkar Ankalkope, Kunal Runwal, Aliasghar ArabAbstract
We study action-conditioned monitoring of autonomous-vehicle behavior in semantically unusual driving scenes. The target is whether the executed ego action is appropriate for the scene: the same scene can admit both normal and anomalous behavior, so visual unusualness alone does not determine the monitoring label. A Vision-Language Model (VLM) first predicts the scene-required action from an outcome-hidden video window; the monitor then compares that expectation with the realized ego-motion trajectory under an explicit compatibility rule. To study this monitoring task, we contribute a six-field taxonomy of 112 paired scenarios spanning both failure polarities (42 derived from documented incidents), a generated video corpus with estimated trajectories, and an exploratory two-stage monitor on that corpus. On 235 clips from 15 scenario families, the two-stage protocol with a fixed T-2.5 s window obtains 83.0% accuracy and anomaly recall 0.773, versus 74.5% and 0.536 for a single-stage video-only baseline; specificity is 0.880 versus 0.928.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07540
PDF
-
Concertina: Embodying Manipulation and Cognition in One Diffusion Vision-Language Model
2026-11-05 06:20:37Chengcheng Wang, Wei He, Wenhao Li, Hongguang Li, Kai Han, Jianyuan Guo, Chang XuAbstract
Most vision-language-action (VLA) policies decouple manipulation from cognition by bolting an external action mechanism onto a vision-language model (VLM)--either quantizing actions into discrete tokens whose errors bear no stable correspondence to physical displacements, or delegating continuous trajectory generation to a separate action expert whose gradients compete with or are blocked from updating the VLM backbone. We argue that manipulation and cognition should instead be embodied in the same model, shifting from a decoupled VLA to an Embodied Vision-Language Model (eVLM). We introduce Concertina, an eVLM that places continuous trajectory representation, blockwise generation, and physical-coordinate supervision directly on the computation and parameter path of a shared diffusion VLM backbone. Each control timestep is encoded as one continuous latent action token in the backbone hidden space, and the shared Transformer reconstructs temporally ordered action blocks via the same corrupt-and-reconstruct operator used for multimodal pretraining. Active action projections account for only 0.21% of parameters in the 4.46B model with zero separate action-generator layers, compared with 16.5%-35.1% dedicated action-expert capacity in representative continuous VLAs. Using our proposed Action Interface Audit, we confirm that cross-time trajectory coupling emerges in the middle and late layers of the shared backbone rather than at the action interfaces. On standard benchmarks, Concertina achieves 98.15% average success on regular LIBERO, 85.9% on the 10,030-task LIBERO-Plus benchmark, and 4.142 average completed chain length on CALVIN ABC-D. Code: this https URL Hugging Face: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2611.07513
PDF
-
Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios
2026-11-05 06:17:01Zhenlong Dai, Zhuoluo Zhao, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan ChenAbstract
The rapid development of large language models (LLMs) for code, which closely aligns with the practical needs of real-world software development, has sparked growing attention in repository-level code completion. However, existing Code LLMs present challenges in focusing on suitable contexts from the repository and in deeply reasoning about cross-file dependencies. To address these challenges, we propose a novel reinforcement learning framework for repository-level code completion. To better understand both in-file and cross-file contexts, we employ identifier-driven intent recognition to capture completion intent, thereby improving the model's performance in real-world scenarios. To enhance cross-file reasoning, we propose a reward-driven completion learning to effectively reward in complex repository completion scenarios. To guide LLMs in completing code that aligns with intended functionality and repository context, we introduce a selective-exploration strategy that directs the model to focus on low-confidence, high-reward tokens, promoting the exploration of valuable, underexplored completion patterns. Experimental results show that our approach significantly improves the performance of Code LLMs. The code and the dataset are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07510
PDF
-
DelegateEval: Evaluating Platforms for Personal External Service Agents
2026-11-05 06:13:41Jichao Li, Jinrong Lu, Manjiang Yu, Zhixuan LiuAbstract
AI agents that work for an individual over time may also help that individual serve external clients. We define a personal external service agent as an agent authorized and continuously managed by a specific individual to accept client requests, deliver work, and provide ongoing support using that person's knowledge, experience, professional methods, and service boundaries. Such agents could allow individuals to serve more clients with less direct involvement and generate economic value at scale. We propose DelegateEval, a platform-level evaluation framework for agent systems that may combine large language models, reusable skills, protocols such as MCP, and executable tool environments. It covers eight dimensions: ease of creation, service discovery and matching, delivery quality, expertise inheritance, service continuity, learning and improvement, reliability and governance, and efficiency and value. These dimensions assess whether a platform enables people with different backgrounds to turn their expertise into ongoing services that deliver verifiable work, develop capabilities through experience, and remain economically feasible. We present the framework and an experimental design. Complete datasets, executable environments, a unified scoring protocol, and cross-model results remain to be developed and empirically validated.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07508
PDF
-
MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports
2026-11-05 05:45:20Hongyu She, Yiling He, Mengda Xie, Yiping Liu, Xingzhi Qian, Zhan Qin, Lorenzo CavallaroAbstract
Mapping behavioral intelligence in malware analysis reports to ATT&CK techniques supports threat analysis and defense, but reliable identification remains challenging. Supporting evidence is often scattered across long, heterogeneous reports, while closely related techniques share behavioral cues and differ only in subtle but decisive details. While large language models (LLMs) can use external knowledge to interpret reports, they may assign techniques based on plausible associations rather than sufficient evidence. We present MEvince, a knowledge-constrained LLM reasoning framework for report-level malware technique identification. Its core is a shared behavioral representation connecting report observations to technique definitions. This representation is built through agentic mining of technique documentation and supports two online stages: 1) primitive-guided extraction uses behavioral primitives to structure LLM-extracted observations, link them to source passages, and group dispersed evidence; 2) evidence-aligned retrieval matches this evidence to technique profiles through the same concepts, retaining likely candidates and confusable alternatives for LLM comparison of distinguishing behaviors. Controls at both stages validate evidence references and check technique-specific requirements. The representation also supports adaptation without parameter updates, where offline agentic audits diagnose concept weaknesses and refine extraction or retrieval policies. We evaluate MEvince against 11 baselines spanning four method families using a dataset of 610 public malware reports referenced by MITRE ATT&CK. MEvince improves exact-ID F1 over the strongest baseline by 17.4%, and its concept-guided retrieval increases gold-label candidate coverage from 31.6% to 47.9%. With a small adaptation set, offline refinement yields further gains and outperforms baselines that update model parameters.
Abstract (translated)
URL
https://arxiv.org/abs/2611.07486
PDF
