Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• Small LLMs10+400.0%
• Training & fine-tuning48+200.0%
• Robotics24+200.0%
• Computer vision37+164.3%
• AI safety34+161.5%
• Evals72+100.0%
• Image & video generation26+100.0%
• Code models15+66.7%

• arXiv cs.CVOct 17

  Spectral-Aware Proposal Enhancement for Diffusion-Based Multispectral UAV Multi-Object Tracking

  Xu Lin, Tingfa Xu, Tianhao Li, Haolin Qin, Huawei Gao +2

  Multispectral UAV multi-object tracking (MOT) with oriented bounding boxes remains challenging due to small targets, cluttered backgrounds, and unstable inter-frame associations. Although diffusion-based MOT provides an effective iterative proposal refinement paradigm, existing diffusion-based trackers lack dedicated designs for exploiting multispectral cues in proposal initialization and confidence calibration, limiting tracking robustness in complex UAV scenarios. This letter proposes DSATrack, a diffusion-guided spectral-aware tracking framework for multispectral UAV MOT. Specifically, a lightweight spectral encoder injects multispectral information into the RPN branch through feature fusion, enabling the RPN head to generate high-quality object-aware proposals. These proposals are then injected into the initial proposal set to provide reliable spatial priors for diffusion refinement. Furthermore, a spectral-saliency confidence modulation strategy recalibrates refined tracking confidence according to local multispectral saliency contrast before score thresholding, enhancing spectrally reliable candidates while suppressing unreliable ones. Without modifying the original…

  PDF
• arXiv cs.AIOct 17

  Selm: Self-Evolving Library Management for Multi-Skill Agent Optimization

  Mengxi Hu, Yuxuan Hu, Jinbo Su, Ke Wang, Honghao Shi +4

  Large language model (LLM) agents increasingly use skills as a lightweight way to acquire task-specific knowledge. Recent work enables skills to evolve from task trajectories. However, these methods often lack systematic management of evolved skills, making it difficult for agents to reuse and accumulate skills across domains, thus limiting performance on subsequent tasks.To reliably accumulate, reuse, and maintain useful skills across tasks, we present SELM (Self-Evolving Library Management), a framework that formulates skill evolution as library-level management. SELM jointly manages skill retrieval, updating, and lifecycle by maintaining skill confidence and utility signals. It introduces utility-aware retrieval to select useful skills, a Map-Reduce framework to generate targeted updates from task-specific experience, and lifecycle controls to retain or remove skills based on their effectiveness. These mechanisms enable the skill library to continuously accumulate useful experience while preserving and pruning skills across tasks, improving agent performance on complex tasks across diverse domains. We evaluate SELM on four agent benchmarks covering diverse tasks and execution…

  PDF
• arXiv cs.CLOct 17▲ 5

  Muse Glimmer 30B: An On-Device Agentic Model

  Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed, Juan C. Angeles Acuna, Alexis Audran-Reiss +324

  We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer integrates multi-step reasoning, reliable tool use and failure recovery into a single model that runs locally on consumer devices without requiring cloud infrastructure. The model accepts text and image inputs and produces text outputs, was trained on data from over a hundred languages, and is quantized to approximately 4-bit precision for efficient single-GPU inference. Muse Glimmer achieves state-of-the-art performance for its size class on agentic benchmarks, setting a new standard compared to the models of its size: Gemma4-31B and Qwen3.6-27B on tool use, multi-step planning, and agentic task completion. We release the model under the Apache 2.0 license to foster open-source development of capable, safe, local AI agents.

  PDF
• arXiv cs.LGOct 17

  Uncovering Semantic Hierarchies in Text-Attributed Graphs via Variational EM-based LLM-GNN Synergy

  Yunhui Liu, Xudong Jin, Qizhuo Xie, Chunhui Zhao, Xiao Luo +3

  While hierarchical structures are intrinsic to organizing human knowledge, current representation learning on text-attributed graphs predominantly operates on flat semantic spaces, overlooking the rich coarse-to-fine granularity inherent in real-world data. To bridge this gap, we propose SHiFT, which synergizes the reasoning power of LLMs with the structural representation capability of GNNs within an Expectation-Maximization (EM) paradigm. In the E-step, we harness LLMs as expert taxonomists to induce an explicit semantic tree, introducing a lightweight Mapping & Diagnosis strategy that reduces inference costs by surgically updating the hierarchy only when anomalies are detected. In the M-step, we align the GNN encoder with this induced hierarchy from complementary perspectives, including clustering partition, topological skeleton, and semantic concepts. Theoretical analysis interprets SHiFT as a generalized Variational EM algorithm. Extensive experiments demonstrate that SHiFT not only achieves state-of-the-art performance but also uncovers high-quality, human-readable taxonomies. Our code can be found at https://github.com/Cloudy1225/SHiFT.

  PDF
• arXiv cs.CROct 17

  Narratives Mislead: An Empirical Study of How LLMs Misjudge CVSS Severity in Bug Bounty Reports

  Ruitao Feng, Yuekang Li, Yao Zhang

  Bug bounty platforms receive vulnerability reports faster than vendors can triage them, and Large Language Models (LLMs) are increasingly considered for assigning the Common Vulnerability Scoring System (CVSS) severity that drives prioritization. Prior evaluations score short CVE descriptions and report accuracy, but deployment depends on how models err, not only how often. CVSS gives each metric a formal meaning that departs from how researchers describe impact in narrative reports, and model rationales suggest that errors concentrate where the two diverge; we ask whether this pattern is systematic. From 4,281 publicly disclosed reports mined from Huntr and HackerOne, we build a benchmark of 240 Huntr reports with vendor-validated CVSS vectors and evaluate eight LLMs under four prompting strategies and fine-tuning, measuring errors by severity class and score and analysing sub-vectors on individual reports. The best prompting configuration reaches only 49.58% level accuracy, ten points above always predicting the majority level, and fine-tuning a 7B model raises this to at most 56.25%, an optimistic upper bound. Errors are directional: models overestimate far more often than…

  PDF
• arXiv cs.CVOct 17

  Beyond Geometric Closure: Measuring and Diagnosing Mechanical Consistency in Visual Dynamics

  Qibin Gu, Yunfeng Yan

  Visual accuracy, geometric validity, and agreement with applied forces are distinct requirements for visual dynamics. We introduce a diagnostic framework that connects reaction-free SI measurements to controlled interventions on coordinate readout, training integration, and actuator response. Reference replay calibrates the measurement path, while continuous scoring exposes progress against fixed engineering targets. With three seeds per setting, we evaluate KeyCLD and CON across 343 planar assemblies at 64/256 pixels and V-JEPA + AC and LingBot-VA on 100 shared spatial test assemblies. CON reduces image MSE by 37.6%/37.2% relative to persistence, yet neither planar model attains valid native geometry. At 256 pixels, calibrated RGB replay places forecast errors far above the reference measurement floor. Exact-state KeyCLD has identical geometric pass rates under Euler and RK4 training, yet its score rises from 52.65 to 64.30 as force and energy errors decrease. In both spatial pathways, CAD/IK reconstruction restores geometry while mean actuator residuals exceed five times the engineering targets. These diagnoses distinguish coordinate correction, numerical improvement, and…

  PDF
• arXiv cs.CLOct 17

  Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs

  Chengyu Xie, Fei Shen, Shuyi Miao, Yue Feng, Jian Yu +3

  The safety capabilities of large language models (LLMs) are highly uneven across different languages, often allowing cross-lingual attacks to bypass safety guardrails. Existing alignment methods predominantly rely on external alignment signals and provide limited insight into underlying neuron-level mechanisms, making it difficult to provide a unified internal target for cross-lingual safety interventions. To address this, we analyze cross-lingual safety behavior at the neuron level and identify a compact set of safety-related neurons shared across languages, termed the safety kernel (SK). Specifically, we first utilize multilingual parallel safe and unsafe prompts to compute safety contrast with activation responsiveness (SCAR) scores, identifying language-wise safety-neuron candidates from internal activation patterns. We then intersect the resulting language-wise safety-neuron sets to obtain the SK, and validate its functional relevance to cross-lingual safety behavior through activation suppression and activation-state transfer interventions. Finally, building on the SK coordinates, we introduce SK-Masked LoRA, which constrains LoRA adaptation to the feed-forward network…

  PDF
• arXiv cs.LGOct 17

  How Much Do Activation Monitors Benefit from Original Model Computations?

  James Oldfield, Shawn Im, Jay J Culligan, Philip Torr, Sharon Li +1

  One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and outputs alone. However, recent studies begin to question the premise that activations provide a unique window into model behavior. In this paper, we study how much of activation monitors' success depends on access to the original behavior-generating computations. Within a fixed choice of target model and monitoring architecture, we compare how well monitors trained and evaluated on trajectories that differ in computational context can predict the behavior of the original execution, after the transcript is changed in a controlled manner (e.g., its exact text, or chat formatting). We first find that much performance can be recovered without access to the original behavior-generating trace (in up to 4 models across 2 counterfactual monitoring tasks), but a mild yet consistent advantage to native-trained monitors remains, outperforming strongest controls by up to 0.014 AUROC. Interestingly, we find monitors trained with native access have notable uplift on original examples whose behavioral label changes…

  PDF
• arXiv cs.AIOct 17▲ 6

  HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference

  Wanyi Chen, Wanqin Shen, Yuanchen Shi, Zhensu Sun, Fang Kong

  Evaluating software agents on a full benchmark is expensive. A small task subset can preserve agent rankings while yielding inaccurate scores. Historical responses provide useful structure, but tasks with identical source responses can have different outcomes for a new target agent. We introduce Hierarchical Score Posterior Recovery (HSPR), which combines source-fitted response factors with uncertain group success rates. Observed target outcomes update the posteriors over the target latent state and group rates; posterior-guided acquisition selects subsequent tasks. Its score-based criterion equals the expected one-step reduction in full-score posterior variance. Observed successes and posterior-predictive counts for unqueried tasks yield a full-score posterior. The final estimate uses its median with source-selected calibration. At a 10% task budget on four task banks from the SWE-bench family, HSPR achieves the lowest mean absolute error (MAE) on three banks and the lowest maximum absolute error (MaxErr) on all four among the methods compared. Removing group uncertainty or replacing adaptive queries increases macro MAE in the respective controls. Macro MAE decreases across…

  Code
• arXiv cs.SEOct 17

  From Candidate Admission to Task-Level Return: Auditing LLM-Generated Code under Execution Contracts

  Hiroyasu Usami, Keisuke Hara, Ayato Tsuboi, Naohiko Matsuda

  Admission rules retain generated programs, whereas selection policies return one candidate per task. We audit how these decisions interact with execution contracts in two separately frozen, disjoint HumanEvalPlus cohorts, each comprising 32 tasks, four samples per task per profile and two served profiles. Under the inline execution contract, a structural-and-self-test screen admits 4-9 expanded-suite nonpasses per 80-107 admissions and excludes 14-43 suite passes per 128 planned attempts. A restricted module-supply condition adds 20 and 14 passing admissions for one profile in the respective cohorts, plus one follow-up nonpass, and reduces the excluded suite passes to 14-23. All fixed first-admitted outcomes and abstentions remain unchanged. In the original pool, the added passes enter already all-passing admitted pools; in the follow-up, four of 24 common sample orders lose one passed task. Selected-subset diagnostics separately address registration-sensitive completion and reference-relative assertion disagreement, accounting for input domains and comparator tolerances. In these high-pass pools, candidate retention and task-level return diverge and are reported separately.…

  PDF
• arXiv cs.CVOct 17

  IntriAdapt: Generalizable Intrinsic-Guided Test-Time Adaptation for Metric Geometry Estimation

  Jiaxing Chen, Zizheng Yan, Jingyu Zhuang, Jinwei Chen, Shuguang Cui +2

  Recovering metric 3D geometry from images is fundamentally ill-posed due to perspective projection ambiguity. Current geometry models incorporate supplied or predicted intrinsics during inference, but do not use them to supervise model adaptation. To refine these predictions, test-time adaptation (TTA) typically relies on external depth measurements. In this paper, we instead use camera intrinsics as an output-side geometric verifier. Comparing the point cloud's viewing rays with those defined by the known intrinsics yields a direct measure of geometric inconsistency. We propose \textit{IntriAdapt}, a TTA framework that minimizes this closed-form geometric residual. By optimizing a lightweight LoRA adapter on a frozen geometry foundation model, our method aligns the prediction with the specific camera model without depth sensors or external priors. We further extend this approach to video sequences, demonstrating that adapting a short sequence generalizes to other sequences captured by the same camera. The adapted model processes held-out images in a feed-forward pass, without repeating optimization for each frame. Experiments on ten single-image and seven sequence benchmarks…

  PDF
• arXiv cs.CVOct 17

  SCOPE-VSR: A Broad-Coverage Training Dataset for Video Super-Resolution

  Gengyu Liao, Yechun Yong, Zheng Chen, Jianze Li, Ziqing Zhang +2

  Open-domain video super-resolution (VSR) requires temporally coherent details across widely varying scenes and subjects. However, existing training datasets are often semantically imbalanced and insufficiently diverse. We address this data bottleneck with a structured curation pipeline for open-domain VSR, SCOPE. In this pipeline, we combine task-oriented video selection with hierarchical semantic rebalancing. Applying this pipeline to a large-scale collection of data sources, we construct the SCOPE-VSR dataset for training and SCOPE-test for testing. SCOPE-VSR has approximately 27k videos and provides balanced and diverse coverage of various real-world scenarios and subjects. We further develop GraCo-VSR, a novel framework for one-step video restoration. GraCo-VSR adopts a reliability-aware design with explicit supervision to reduce degradation-induced distortions in motion and texture guidance, allowing the model to benefit more effectively from the diverse training content in SCOPE-VSR. Evaluations show that our model achieves strong reconstruction fidelity and perceptual quality. Our code is available at: https://github.com/gyliao2768/SCOPE-VSR.

  PDF
• arXiv cs.CVOct 17

  Dynamic self-ensemble on multi-exit residual vision transformer for small-data image classification

  Stephen Ekaputra Limantoro, Yan-Kai Wang, Ching-Chun Huang, Hong-Han Shuai, Wen-Huang Cheng +2

  Vision Transformer (ViT) has garnered increased attention for image classification in recent years. However, ViT is notorious for its data-hungry problem as it achieves high-performance results when only trained on large-size datasets. In this paper, we study how ViT specifically works on small-scale datasets with limited data where the availability of image data is often constrained in practice, especially in fields such as medical imaging. To mitigate the issue, we designed a multi-stage residual ViT, dubbed ReSEViT, with the self-ensemble method to utilize multi-level information from intermediate features. Due to the complex decision boundaries for classifications, relying on a single classifier can lead to prediction errors. Hence, we propose a new learning method for ViT, named self-ensemble learning, which ensembles multi-stage classifiers in a single model. Our self-ensemble comprises a novel approach, Dynamic Learner Selection (DLS), to adaptively select the importance of different stages. ReSEViT incorporates residual token embeddings which is a ResNet-like block to model effective local structures alongside with transformer blocks in each stage. The integration of…

  PDF
• arXiv cs.LGOct 17

  TCMScience: An Autonomous Scientist for Traditional Chinese Medicine

  Yanlan Kang, Ruiqi Liu, Xinpei Gu, Tzu-Yi Lei, Shuai Xu +2

  Traditional Chinese medicine (TCM) research connects classical texts, medicinal entities, molecular assays, computational predictions, and clinical studies. An autonomous research agent must preserve the inferential boundaries between these evidence types while coordinating analysis across heterogeneous resources. We introduce TCMScience, a scientific knowledge-discovery agent that separates language-model proposals from execution and release authority. Its architecture combines a trusted kernel, a scientific compiler, and claim-support contracts: plans are compiled into typed operations, execution is bounded by explicit permissions, and candidate findings are checked against source provenance, study design, and claim scope before release. The full capability registry contains 117 public-source connectors with 444 typed operations across 29 domains and 150 native tools across 12 domains; the TCM data hub catalogs 136 databases, 76 dataset specifications, and 84,294 formula-source records. These resources support model-independent workflows through browser and local execution interfaces. In a network-pharmacology analysis of Gegen Qinlian Tang, replacing the whole-proteome…

  PDF
• arXiv eess.IVOct 17

  Severity-Channel Conditioning: An Injection-Level Study for Consumer-Device Deblurring

  Abdullah Al Shafi, Kazi Saeed Alam, Sumaiya Rahim Suma, Sk. Imran Hossain

  Motion-deblurring models lose substantial accuracy when transferred from professional cameras to smartphone-derived imagery. This paper studies whether a severity descriptor, partly derived from the paired sharp target, helps adaptation on the iPhoneBlur consumer-device benchmark. Under a shared update budget, input concatenation of a severity map is compared with global feature modulation by capture metadata, spatial feature modulation by the severity map, and a tier-contrastive output objective, together with an unconditioned spectral-loss control, all fine-tuned from the same domain-adapted latent-diffusion baseline. The primary experiment is an oracle diagnostic: target-derived information is supplied at inference. For the evaluated model pair, input concatenation improves overall peak signal-to-noise ratio from 31.23 to 31.30 dB, whereas feature modulation, the contrastive objective, and the spectral-loss control do not exceed the baseline. The gain is positive on 87.2% of test images and on 14 of 15 held-out source videos; this video-level analysis describes the evaluated checkpoint pair and does not establish robustness to retraining, and three training seeds are reported…

  PDF
• arXiv cs.LGOct 17

  AdamPM: Memory-Efficient LLM Optimization via Moment Pooling

  Xiaowei Ji, Lishan Xu, Jianing An, Jie Luo, Wenjun Wu +1

  Adam is widely used for training large language models (LLMs) owing to its strong optimization performance and training stability, but its element-wise estimation for the first and second moments incur substantial memory overhead. Although numerous memory-efficient optimizers have been proposed, many incur additional computational overhead or require additional tuning of hyperparameters. Consequently, Adam remains a dominant and reliable choice for LLM pre-training. We propose AdamPM (Adam with Pooled Moments), a simple and memory-efficient variant of Adam that groups adjacent moment entries along the row or column dimension and represents each group by a single shared mean. AdamPM can well inherit Adam's hyperparameter settings and is readily integrated into existing Adam optimizer implementations, with less memory overhead. We systematically investigate pooling of both first and second moment estimates and identify second moment pooling as the effective design. With a group size of $s$, AdamPM reduces second moment memory to $1/s$ of the original requirement. Extensive experiments on language model pretraining, fine-tuning and multimodal learning demonstrate that AdamPM…

  PDF
• arXiv cs.AIOct 17

  CADS: Measuring the Incremental Contribution of LLM Proposers in Sequential Biological Screens

  Guanxing Chen, Nihui Shao, Haohuai He, Zhenchao Tang, Pengwei Hu +1

  Large language models are increasingly used to guide sequential biological screens, yet standard evaluations rely on raw hit counts that conflate a proposer's value with the discovery capacity of the underlying algorithmic harness. Adaptive sampling and corrupted experimental readouts also leave standard feedback comparisons without a false-discovery guarantee. We present Certified Agentic Discovery Screens (CADS), an error-controlled measurement framework that quantifies a proposer's incremental value against an identical LLM-free loop. By integrating capped likelihood-ratio bounds, e-processes, and complete-family e-BH, CADS controls the terminal false discovery rate under the stated null and corruption conditions despite arbitrary dependence, adaptive sampling, and optional stopping. In DepMap-backed simulations, CADS exposes two evaluation artifacts: the LLM-free harness alone clears the feedback gate, and raw origin counts overstate LLM contributions because LLM picks displace fallback discoveries. On the initial 20 seeds, supplying tested-candidate history to Qwen2.5-7B shifts its net contribution from +0.35, with a 95% interval covering zero, to +2.90, with the interval…

  PDF
• arXiv cs.CLOct 17

  Training with Ciphers to Enhance In-Context Terminology Learning For Translation from Rare Languages

  Deevyanshu Malu, Deeptanshu Malu, Sunita Sarawagi

  Fine-tuning LLMs with in-context examples (IC-Train) lets translation models adapt to new parallel data at deployment, but it is unclear whether they actually learn the translations of rare terms from those examples. We formalize this capability as in-context term learning (ICTL). We show that standard IC-Train develops this capability only weakly, and propose RareCipherFT, which strengthens it without any lexical resources. RareCipherFT pairs each training target with in-context examples that share a rare term with it. It then replaces that term with a character-shuffled cipher in both the context and the reference, so the term can only be recovered by copying from context. The ciphered fraction of training data is annealed to preserve translation quality. Across seven translation directions between English and Tamil, Assamese, Mizo, Nepali and Hausa, and four models from 1B to 7B parameters, RareCipherFT raises term recall over standard IC-Train by 5-15 absolute points without lowering COMET. Probes using synonyms, nonce words and controls for shared surface context show that these gains come from linking source terms to their in-context translations rather than from shortcuts.

  PDF
• arXiv cs.CVOct 17

  Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing

  Yujia Yang, Quan Yuan, Jiawei Fan, Yang Li, Tiange Fu +3

  Vision-Language-Action (VLA) models offer a promising paradigm for autonomous driving. However, the massive parameter scale of VLAs strains onboard computational resources during real-time inference. This directly increases energy consumption and limits vehicle battery range, making it critical to minimize computational overhead without compromising driving capability and explainability. Current research on efficient VLA-based driving focuses on sequential adaptation (\textit{e.g.}, Chain-of-Thought and token adjustment), leaving structural adaptation underexplored despite parameter redundancy across dynamic driving scenes. To address this gap, we propose Scene-Adaptive VLA, an efficient framework leveraging dynamic layer routing to adjust active parameters based on real-time scenes. Inspired by the temporal continuity of scenes and model predictive uncertainty, our approach characterizes model-perceived scene complexity via frame-level temporal scene variations and decision deviations. To uncover latent scene-to-parameter correspondences, we encode this characterization into scene-aware tokens, alongside two specialized queries. A budget-conditioned layer routing mechanism…

  PDF
• arXiv stat.MLOct 17

  Conditional Weight of Evidence for Gradient-Boosted Credit Models: Estimation, Additivity and Its Relation to Adverse Action Reasons

  Agus Sudjianto, Denis Burakov

  Traditional weight of evidence assigns a credit characteristic a value based on its association with default across a population. Credit analysis also requires an assessment of that characteristic in the context of an individual applicant's record. We study conditional weight of evidence for this purpose. It measures the change in default log odds from observing a characteristic after the remaining credit information is known. Its sign identifies whether the characteristic adds adverse or favorable information for that applicant, and its magnitude measures the strength of that information. The same characteristic value can therefore receive different assessments for applicants with different payment histories or other credit attributes. We develop estimators using gradient-boosted trees and evaluate their accuracy in a bureau-style simulation. Regressions of the full model's predicted probabilities recover conditional evidence more accurately than separate models fitted to default outcomes, provided the full model is accurate. They also recover a deliberately constructed file-age effect whose direction varies with utilization and is often missed by marginal weight of evidence.…

  PDF