Artificial Intelligence · Cross-listed from cs.CR
Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD
Isha, Deepak Singh, Devesh Kumar et al. (+3 more)
Conventional BB84
Quantum Key Distribution (QKD) systems rely on a fixed 11%
Quantum Bit Error Rate (QBER) threshold to detect eavesdropping. However, stealthy attacks can remain below this threshold while still compromising channel security. This paper proposes a temporal QBER based machine learning framework for detecting and classifying eavesdropping attacks in BB84 QKD systems. Rather than relying on average session level QBER, the framework extracts 63 physics-informed temporal features capturing burst behavior, temporal instability, basis dependent asymmetry, and QBER loss interactions. Random Forest, XGBoost, and Support Vector Machine with a Radial Basis Function kernel (SVM-RBF) classifiers are evaluated on seven eavesdropping attacks and a normal channel scenario under noisy and lossy conditions. Averaged over ten independent runs, XGBoost achieves the best performance with 88.01% (0.47%) accuracy and a macro F1 score of 0.8803, while SVM-RBF performs comparably, confirming the robustness of the proposed features. Evaluated as a binary attack-versus-normal detector for comparison with conventional monitoring, a fixed 11% QBER threshold achieves only 25.82% accuracy with a False Negative Rate (FNR) of 0.8477, whereas the proposed framework reduces the FNR to 0.0198, substantially improving detection of stealthy attacks that evade threshold-based monitoring. SHapley Additive exPlanations based (SHAP) explainability shows that physics-informed temporal and channel derived features are highly discriminative for identifying eavesdropping strategies. These results demonstrate that temporal QBER driven machine learning provides an accurate, explainable, and practical framework for multi attack security monitoring in BB84 QKD systems.
Read the full abstract ▾
All authors Isha, Deepak Singh, Devesh Kumar, S.K Pal, Praful Hambarde, Amit Shukla
Artificial Intelligence · Cross-listed from cs.LG
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity
Chinmoy Mitra, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood et al. (+2 more)
Federated learning (FL) enables aircraft fleet operators to jointly train remaining-useful-life (RUL) models from engine sensor telemetry without sharing raw data. This study examines two complementary challenges: benign heterogeneity, where honest operators observe different operating conditions and fault modes, and
adversarial heterogeneity, where compromised operators submit poisoned updates. We conduct a controlled, safety-oriented evaluation using a multi-task one-dimensional convolutional neural network and a structurally non-IID partition of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS)
benchmark. We compare four remedies for benign heterogeneity and evaluate five attacks against four aggregation methods, including a physically motivated sensor-value
backdoor designed to mask engine degradation. Shared-representation personalization closes approximately 70% of the local-to-centralized root-mean-square-error gap, compared with 21% for proximal regularization and 10% for server-side reweighting. The
backdoor achieves a 94.9% attack success rate against standard averaging while leaving clean accuracy statistically unchanged, demonstrating that accuracy alone cannot certify model safety and that attack success must be evaluated explicitly. Krum reduces attack success by an order of magnitude and is the only evaluated aggregator that withstands coordinated attackers, whereas personalization alone provides no protection. Combining personalization with robust aggregation restores robustness (2.8% attack success) with only a small accuracy cost, revealing a trade-off between robust update selection and collaborative representation learning. Results remain consistent across client counts and on a harder six-condition
dataset. Code and data partitions are released for reproducibility.
Read the full abstract ▾
All authors Chinmoy Mitra, Md. Mehedi Hasan Nipu, Mohammad Sakib Mahmood, Md. Rakibul Islam, M. F. Mridha
Artificial Intelligence · Cross-listed from cs.CL
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Changle Qu, Sunhao Dai, Hengyi Cai et al. (+4 more)
Tool-Integrated
Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained credit assignment in long-horizon TIR scenarios. On-policy self-
distillation offers denser signals through teacher branches with privileged context, but existing approaches typically derive such context from ground-truth answers or retrieved skills, which may not reflect the states actually visited by the
agent. Moreover,
token-level supervision fails to capture the turn-level structure of tool interactions. To address this, we propose TurnSight, a turn-level hindsight self-
distillation framework that derives supervision directly from execution-conditioned hindsight. It then constructs multiple hindsight views with different lookahead horizons and selects reliable supervision through cross-horizon directional agreement. Finally, the selected hindsight signal is normalized across sibling rollouts and used to adaptively modulate RL advantages while preserving their original optimization direction. Extensive experiments on three
benchmarks demonstrate the effectiveness of TurnSight. Our codes are available at https://github.com/quchangle1/TurnSight.
Read the full abstract ▾
All authors Changle Qu, Sunhao Dai, Hengyi Cai, Yuqi Zhou, Xinran Chen, Simon, Jun Xu
Artificial Intelligence · Cross-listed from cs.LG
Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and Reproducibility
Mohsen Hariri, Weicong Chen, Nahal Shahini et al. (+11 more)
Large
language models can solve harder
reasoning problems with more inference-time compute. The term "test-time scaling," however, covers several inference
algorithms: extending deliberation along one trajectory, sampling completed candidates and aggregating them by voting or verification, and searching over partial states. These
algorithms differ in statistical structure, compute requirements, and failure modes. Treating them as interchangeable under a scalar "budget," or reporting accuracy without specifying the inference protocol, makes results difficult to compare across studies. We study test-time scaling along three axes. First, we formalize it as budgeted inference over the implicit prefix tree of an autoregressive model and distinguish single-trajectory sequential scaling, leaf-level scaling with terminal reduction, and prefix-level scaling. Second, we treat the full inference system as the evaluated object and separate end-to-end performance from candidate-bank diagnostics. We introduce an evaluation profile whose coordinates and simple functionals recover or bound common repeated-sampling metrics, and require compute accounting and uncertainty estimates that match the protocol. Third, we distinguish exact replay from distributional reproducibility and state the requirements for each. We also organize open-weight
reasoning models by model-side and interface mechanisms. Our empirical study covers broad knowledge, symbolic
reasoning, and competition mathematics, and we publicly release 1,403,520 sampled model attempts. The project website is available at https://mohsenhariri.github.io/scorio/tts. The released
datasets are Trace (https://huggingface.co/
datasets/harimo/scorio-trace), Lite (https://huggingface.co/
datasets/harimo/scorio-lite), Math (https://huggingface.co/buckets/harimo/scorio-math), and SuperGPQA (https://huggingface.co/buckets/harimo/scorio-gpqa).
Read the full abstract ▾
All authors Mohsen Hariri, Weicong Chen, Nahal Shahini, Vikash Singh, Kai Ye, Amirhossein Samandar, Debargha Ganguly, Sreehari Sankar, Yanyan Zhang, Shouren Wang, Jerry Peng, Biyao Zhang, Michael Hinczewski, Vipin Chaudhary
Artificial Intelligence · Cross-listed from cs.PL
Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?
Hailong Jiang, Feng Yu, Emran Hossain et al. (+4 more)
Optimizing compilers miss profitable transformations when their enabling semantics are absent from the analyzed program representation. We ask whether large
language models (LLMs) can recover such semantics from heterogeneous C/C++ context and realize them as validated, contract-preserving artifacts. We introduce SeGaBench, an executable
benchmark containing 100 synthetic and 20 source-backed cases spanning low-level assumptions, data-structure invariants, and high-level semantic lifting. Each case includes hidden enabling semantics, an oracle artifact, correctness and semantic validators, and a reproducible performance protocol. We evaluate five LLMs using five independent responses per case. The strongest model produces correct artifacts in 94.8% of responses, achieves at least 1.05x speedup in 83.3%, and obtains a performance success on 93.3% of cases. Nevertheless, correct artifacts often close only part of the oracle gap. These results show that LLMs can complement compiler analysis as speculative semantic proposers, provided that their artifacts are validated and evaluated.
Read the full abstract ▾
All authors Hailong Jiang, Feng Yu, Emran Hossain, Jianfeng Zhu, Mengfei Ren, Qiang Guan, Chunwei Xia
Artificial Intelligence · Cross-listed from cs.CV
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
Zhen Fang, Yu Zeng, Wenxuan Huang et al. (+17 more)
We introduce
Video-DeepResearch (
Video-DR), extending
multimodal agents from static images to continuous
video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration. Preliminary evaluations reveal two critical bottlenecks in current models: (1) modality bias, where
agents bypass visual tools in favor of textual search, and (2) parametric knowledge leakage, where models rely on internal
memory rather than genuine tool-augmented execution. To address these challenges, we propose
Video-DR, featuring a decoupled perception-exploration pipeline with stage-wise tool unlocking that compels exhaustive cross-frame visual grounding prior to web
retrieval. Our framework adopts a two-stage training recipe: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO), enabling autonomous exploration that breaks the imitation-learning ceiling. Furthermore, we curate
Video-DR-Bench, a human-AI collaborative
benchmark comprising 200 complex, multi-hop VQA instances. Empirical results demonstrate that our
Video-DeepResearch-35B-A3B establishes a new state-of-the-art of 64.0% average accuracy, surpassing proprietary Claude-4.5-Sonnet (59.0%) by 5.0 points and significantly outperforming GPT-5 (52.5%) and Gemini 2.5 Pro (57.5%). The 30B-A3B variant achieves 59.3%, competitive with Claude-4.5-Sonnet and demonstrating the effectiveness of our training paradigm even at compact scale. Code: https://github.com/Osilly/
Vision-DeepResearch.
Read the full abstract ▾
All authors Zhen Fang, Yu Zeng, Wenxuan Huang, Yiming Zhao, Shiting Huang, Tianfei Ren, Qi Lu, Qingnan Ren, Qisheng Su, Lionel Z. Wang, Qingyu Yin, Shuang Chen, Zehui Chen, Lin Chen, Zhenfei Yin, Yao Hu, Shaohui Lin, Wanli Ouyang, Shaosheng Cao, Feng Zhao
Artificial Intelligence
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Jinhe Bi, Chennan Zhou, Zengjie Jin et al. (+10 more)
On-policy training has emerged as a powerful post-training paradigm for improving the
reasoning capabilities of large
language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples. We argue that such failures, which we call Golden Negative Trajectories, can still provide valuable
reasoning signals when treated not as demonstrations to imitate, but as flawed trajectories to reflect upon. We identify a Reflection Advantage: for hard problems, reflecting on a flawed trajectory can be easier and more effective than solving the problem directly from scratch. Motivated by this, we propose ReflectRL, a lightweight plug-and-play framework that learns from Golden Negative Trajectories during on-policy training. ReflectRL first uses these trajectories to elicit Reflective
Reasoning, then applies Reflective-to-Direct Policy Transition to transfer the acquired
reasoning behavior back to Direct
Reasoning. Experiments across 9
benchmarks, 4 LLM backbones, and 4 on-policy training methods show that ReflectRL consistently improves
reasoning performance with minimal overhead.
Read the full abstract ▾
All authors Jinhe Bi, Chennan Zhou, Zengjie Jin, Aniri, Shuo Lu, Wenke Huang, Hu Cao, Xun Xiao, Zhihong Zhu, Volker Tresp, Fei Shen, Yunpu Ma, Tat-Seng Chua
Artificial Intelligence
Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations
Zizhao Hu, Nathan Elijah Segura, Mohammad Rostami et al. (+1 more)
Human input reaches
language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, disfluency from conventional transcription and restructuring from AI-backed dictation tools. How do they impact an LLM's performance? In this paper we present HIVE (Human Input-Variation Engine), a suite of voice transcription perturbations and QWERTY keyboard perturbations. We use HIVE to evaluate how robust models are to these perturbations. We present seven findings. (i) Voice transcription perturbations lower accuracy across every instruction-tuned model we test, and it is the structure of the transcription rather than its fillers that carries the cost. (ii) QWERTY keyboard perturbations cost less, and a model absorbs a lot of them before accuracy falls away. (iii) Both trace back to one cause, how many of the question's
tokens survive the perturbation: destroying a
token is what hurts, while adding new ones alongside it costs little. (iv) The gap between the two channels appears only where the answer must be constructed or deduced; on multiple choice there is none. (v) The harm does not solely come from test-set contamination. (vi) It cannot be trained away with lightweight adaptation. (vii) A thinking budget recovers the keyboard channel almost entirely but leaves the spoken registers untouched, and compressed
speech is worse with it.
Read the full abstract ▾
All authors Zizhao Hu, Nathan Elijah Segura, Mohammad Rostami, Jesse Thomason
Artificial Intelligence · Cross-listed from quant-ph
Separating quantum circuits from classical LLMs
Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi et al. (+1 more)
Modern large
language models -
transformers and
diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth
quantum computation and the corresponding bounded-resource classical
language-model architectures in both regimes. Concretely, we exhibit the following: 1. Distributional separation. We give a distribution that is sampleable by $\textsf{QNC}^0$
circuits (i.e., a family of constant-depth
quantum circuits consisting of bounded fan-in gates) that no constant-round
diffusion language model ($\textsf{DLM}$) with shallow scheduling and denoising can sample within constant distance, even when allowed sublinear chain-of-thought and output-
token revision/remasking events, the very features modern $\textsf{DLM}$s rely on. 2. Functional separation. We exhibit a function computable in $\land \circ \textsf{QNC}^0[\log\log n]$ (i.e., a family of O$(\log\log n)$-depth $\textsf{QNC}^0$
circuits, where $n$ is the input length, followed by a single classical $\mathsf{AND}$ gate) such that any constant-depth decoder-only
transformer computing the function must be large: it would have to have width $n^{\Omega(1)}$. Together, our work initiates the study of
quantum advantage in the era of large
language models.
Read the full abstract ▾
All authors Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi, Rik Sengupta
Artificial Intelligence
Interpretable Adaptive Sampling for LLM Test-Time Scaling
Mobina Kashaniyan and Ali Jannesari
Test-time scaling improves LLM
reasoning by generating and aggregating multiple candidate answers, yet many pipelines use fixed per-query budgets that spend the same compute on easy and difficult
prompts. These fixed budgets are also difficult to inspect because they do not explain why a given
prompt receives a particular number of samples. We propose adaptive} test-time scaling with a lightweight fuzzy controller that maps interpretable signals, including estimated
prompt complexity and model confidence, to a per-query sampling budget. The controller assigns fewer samples to easier or more confident
prompts and more samples to harder or less certain
prompts, making inference-time compute inspectable rather than fixed or opaque. We evaluate under a fair-
alignment protocol with matched decoding settings and controlled answer selection, and compare against best-of-$N$, compute-aware scaling, and self-certainty-based baselines on question-answering and mathematical
reasoning tasks. Across models and
datasets, adaptive fuzzy control improves over several standard baselines and remains close to a selector-matched full-budget control while reducing the average number of samples. These findings suggest that interpretable adaptive sampling is a practical direction for more efficient test-time
reasoning in large
language models.
Read the full abstract ▾
Artificial Intelligence
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis et al. (+11 more)
As autonomous
agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is essential for ensuring safety and cooperation. Classical game theory, the dominant framework for modeling rational interaction, is built upon the assumption of `decoupled agency,' where
agents treat their own decision-making as independent of the environment and other actors. Modern AI
agents, however, jointly predict their own future actions alongside external observations. Here, we report a striking finding: when interacting in stylized social dilemmas, foundation model
agents engaging in optimal planning consistently converge to stable cooperation, directly contradicting classical game-theoretic predictions of mutual defection. To understand this phenomenon, we introduce the `embedded
Bayesian agent,' a theoretical model for foundation model
agents. By shifting from decoupled to embedded agency, these
agents model themselves as part of the universe they inhabit, maintaining epistemic uncertainty about their own decision-making
algorithms. We show that by inferring whether others are behaviorally similar, an embedded
agent treats its own deliberation during planning as evidence: a decision to cooperate predicts a similar decision by a similar partner. We formalize this mechanism of similarity inference through the `embedded
equilibrium,' a novel solution concept replacing the Nash
equilibrium to provide a foundational game theory for the social behavior of modern AI
agents.
Read the full abstract ▾
All authors Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis, Rajai Nasser, Roberta Rocca, Seijin Kobayashi, Guillaume Lajoie, Angelika Steger, Blake Richards, Marcus Hutter, James Manyika, Rif A. Saurous, João Sacramento, Blaise Agüera y Arcas
Artificial Intelligence
TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring
Dongjie Yang, Siyan Lin, Leixian Shen et al. (+3 more)
Large
language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-
language (ESL) learners. Effective ESL tutoring, however, requires more than fluent response generation: a tutor must select an appropriate pedagogical action based on learner behavior and dialogue context. Human-tutoring research offers principles for adaptive support, but they are often task-specific and remain insufficiently integrated into LLM-based ESL tutor training and evaluation. We present TACT (Taxonomy-Aligned Conversational Tutor), a human-grounded framework for post-training and evaluating pedagogically adaptive ESL tutors. Drawing on established literature, we develop two complementary taxonomies: the Tutor-Strategy Taxonomy with 13 tutor response strategies and the Student-Move Taxonomy characterizing learner behavior by move type and status. Using these taxonomies, we construct TACTCorpus, which enriches 260 authentic teacher-student conversations with 32,379 annotations and quality-controlled augmented training data. We then post-train Qwen3.5-4B through supervised fine-tuning followed by taxonomy-aligned Group Relative Policy Optimization, producing TACTutor and optimizing it for scaffolding quality rather than reference imitation alone. On TACTBench, a strategy-balanced diagnostic
benchmark comprising 78 authentic tutoring contexts, TACTutor improves over its backbone by 20.30% and outperforms all evaluated proprietary baselines under the same protocol, while maintaining backbone performance on established external educational
benchmarks; in a blinded study with 50 learners, it also receives the highest overall mean rating among the evaluated tutors. We release the data,
benchmark, and model weights, providing an open foundation for developing pedagogically adaptive ESL tutors.
Read the full abstract ▾
All authors Dongjie Yang, Siyan Lin, Leixian Shen, Rui Sheng, Huamin Qu, Zixin Chen
Artificial Intelligence · Cross-listed from cs.CL
Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility
Jo-Ku Cheng, Nikolaos Aletras and Marco Valentino
Pre-pretraining
language models (LMs) on symbolic data can accelerate and improve natural
language acquisition. However, existing pre-pretraining tasks, such as Dyck and procedural
algorithms, rely on narrow primitives that fail to capture the expressive capacity of natural
language. Moreover, prior studies remain restricted to relatively small
token budgets, offering limited insight into skill emergence and representational dynamics. To address these limitations, we propose logic pre-pretraining (Logic-PPT) as a principled initialization strategy, leveraging formal derivations to impart richer structural and linguistic biases. Formal derivations require abstract mechanisms that are central to natural
language, simultaneously binding variables, connecting quantifiers and relational dependencies, and composing predicate-argument structures over long contexts. Scaling our evaluation to a 100B-
token regime, logic pre-pretraining substantially accelerates skill acquisition in LMs, achieving 80% accuracy on linguistic tasks with 36B fewer
tokens than standard initialization, and outperforming alternative pre-pretraining baselines. Mechanistically, formal derivations induce persistent structural reorganization, distinctively characterized by a lower-rank, spectrally concentrated representation space. Crucially, we show that this internal geometry enables improved model compressibility via
pruning, matching the dense baseline performance even at $\approx$33% sparsity.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki et al. (+2 more)
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices, especially in multivariate settings. While transforming time series into images has shown success in
forecasting and classification, it remains unclear how multivariate, high-dimensional series should be mapped to multi-channel images and whether
vision backbones can match time-domain baselines in TSAD. We introduce PRISM, a plug-and-play meta-workflow enabling systematic construction and evaluation of image-based representations for multivariate TSAD. Our evaluation spanning over 7,000 experiments shows that well-designed PRISM configurations are competitive with 24 time-domain baselines, achieving the best VUS-PR on 10 of 14
datasets, with an average improvement of 41% over the best competing method on those
datasets. Further, we identify channelization - how the channel dimension of multi-channel images is constructed - as a critical and previously understudied design dimension, and introduce MSM, a novel statistics-based scheme achieving 11-27% gains over PCA-based alternatives. Finally, ImageNet-pretrained encoders transfer effectively to TSAD, with frozen encoders retaining 92% of fine-tuned performance while training 1.8 times faster. Our code is available at: https://github.com/Smendowski/PRISM.
Read the full abstract ▾
All authors Mateusz Smendowski, Kamil Faber, Piotr Nawrocki, Nathalie Japkowicz, Roberto Corizzo
Artificial Intelligence
The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections
Marco Giunti and Fabrizia Giulia Garavaglia
We reinterpret
Transformer inference by developing a functionally equivalent mechanical-structural description of its functional architecture. Parameterized transformations of
token representations, or transforming concepts, are identified with simple neural networks organized through output-input and output-weight interconnections. This redescription makes explicit an organizational feature that is not equally salient in the standard
matrix description: during inference, the outputs of some networks determine the weights, and hence the transformations, of others. These output-weight interconnections generate
prompt-dependent dynamic transformations and give rise to Sequence-level Interactive Dynamic Parallel Processing (SIDPP). We show that the number of dynamic parameters grows linearly with
prompt length and may become comparable to, or exceed, the number of static parameters fixed through training, a phenomenon we call strong
prompt sensitivity. Philosophically, this shifts the conceptual picture of the
Transformer from one centered on the static structure acquired through training to one that also treats the
prompt-dependent transformations dynamically constructed during inference as constitutive features of its operation. GPT-4.5's recent Turing test results provide a behavioral illustration of this phenomenon. Finally, we identify biological mechanisms morphologically and functionally correspondent to output-weight interconnections, supporting the in-principle neural realizability of SIDPP and motivating
Conjecture T: human neural systems may realize a functional architecture relevantly similar to that of the
Transformer.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Zixun Guo and Simon Dixon
Humans recognize a musical passage even when it is shifted in time or transposed in pitch, indicating a notion of equivariance in the representation space. Our analysis, however, shows that standard music
transformers map such time-shifted or pitch-transposed inputs onto uncorrelated representations: these models become progressively less equivariant as they scale in size or train longer. This suggests that in standard music
transformers, additional model capacity is allocated to memorizing absolute patterns rather than capturing shared musical structures. In this paper, we propose the Equivariant Music
Transformer (EMT), which enforces equivariance through self-
distillation by jointly optimizing a next-
token-prediction and an auxiliary equivariance regularization loss. We find that the additional equivariance loss acts as a beneficial regularizer, simultaneously improving next-
token prediction and producing equivariant latent representations. Through both objective and subjective evaluations, EMT demonstrates superior equivariance and generative capability compared to data augmentation, feature engineering, and state-of-the-art (SOTA) baselines. More broadly, our findings reveal that standard
language modeling methods alone do not capture music's translational
symmetries, and dedicated inductive biases are required to produce better music representations. The code, weights and demos are available online.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Ke Li, Jiayu Chen, Maoliang Li et al. (+5 more)
Efficient long-
video understanding requires
vision–
language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed frame budgets and candidate pools, while
agent-based schedulers achieve adaptivity through costly multi-round
reasoning and interactive search. We propose EcoFrame, a training-free framework for low-overhead query-adaptive visual evidence scheduling. EcoFrame leverages the VLM's inference feedback to determine when to increase the frame budget and where to search for additional candidate evidence. Specifically,
entropy-gated budget scheduling uses output uncertainty to stop early when the current evidence is sufficient or progressively expand the frame budget otherwise. Meanwhile,
attention-guided candidate proposal converts frame-level
attention into a temporal prior, enabling dense local search in informative regions while preserving global coverage when
attention is diffuse. Experiments on
Video-MME, LongVideoBench, and MLVU demonstrate that EcoFrame achieves a better accuracy–efficiency trade-off across multiple VLM backbones. On Qwen2.5-VL, EcoFrame achieves an average accuracy of 64.4, surpassing BOLT at 63.5, while providing a $1.85\times$ speedup over AKS and BOLT. Compared with the
agent-based A.I.R., EcoFrame maintains comparable accuracy with up to a $13.5\times$ inference speedup. Code will be available at https://github.com/AK-DREAM/EcoFrame.
Read the full abstract ▾
All authors Ke Li, Jiayu Chen, Maoliang Li, Zihao Zheng, Hailong Zou, Hengyi Zhang, Xuanzhe Liu, Xiang Chen
Artificial Intelligence
Implementing Causal Perception: Competing SCMs and Situated Fairness
Jose M. Álvarez
Causal perception occurs when
agents with competing Structural Causal Models (SCMs) of the same system infer different probability distributions, including the hypothetical distributions implied by each
agent's SCM under the same set of interventions. It shapes how
agents reason about the system and how they perceive its
fairness. Causal perception is a promising probabilistic framework, but it has remained purely theoretical. This work provides the first implementation of the causal perception framework of Álvarez and Ruggieri (2025). We operationalize structural (
agents disagree on the causal graph) and parametrical (
agents agree on the causal graph but disagree on its weights) causal perception. We design
algorithms for computing interventional and counterfactual distributions and propose suitable distance measures to quantify the disagreement. Using the German Credit
dataset, we illustrate how causal perception affects accuracy and
fairness in a multi-expert decision setting. We show that the perception verdict is sensitive to the choice of distance metric and threshold. We also show that causal perception changes
fairness assessments and threshold-based decisions. Bias proves situated with respect to the
agent's SCM, demonstrating that competing worldviews in
fairness problems cannot be ignored.
Read the full abstract ▾
Artificial Intelligence
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
Matt Ratto, Abhishek Moturu and Daniel Silver
As AI systems are deployed across increasingly diverse social contexts,
alignment can no longer be framed as the optimization of a single, unified set of values. Instead, systems must be able to recognize, represent, and respond to multiple legitimate perspectives. This has led to growing interest in pluralistic
alignment, which seeks to move beyond one-size-fits-all models of appropriate behaviour. However, current approaches often lack a clear account of how values are socially organized, contested, and coordinated in practice. In this paper, we argue that social theory provides essential conceptual and design resources for addressing these challenges. Drawing on established traditions in sociology, we show how perspectives can be understood as structured by roles, shaped through interaction, and distributed across fields of power and expertise. We translate these insights into concrete implications for AI system design, including role-based representations, structured coordination among perspectives, and context-sensitive evaluation. For agentic systems, this requires aligning not only final outputs, but also the role activations, deliberative traces, aggregation rules, and feedback loops through which those outputs are produced. Our contribution is to reposition pluralistic
alignment as a problem of socially grounded coordination rather than output diversification. We outline a design space for systems that engage multiple perspectives in structured and accountable ways, and we identify directions for future work to implement and empirically evaluate these approaches in real-world settings.
Read the full abstract ▾
Artificial Intelligence
When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking
Shaofeng Liang, Runwei Guan, Wenshuo Chen et al. (+7 more)
Resource constraints on
UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficiency. Adaptive
Transformer Trackers, which leverage an input-dependent dynamic routing architecture, have emerged as a representative solution to this challenge. However, we reveal that behind this computation-on-demand flexibility hides a critical structural flaw: the Lipschitz singularity of computational path decisions, which has an unbounded local Lipschitz constant at discrete layer-skipping decision boundaries. This mathematical discontinuity renders adaptive tracking networks inherently unstable: tiny input perturbations can be amplified at the gating modules, causing dramatic changes in the inference
topology. We formally characterize this singularity in the context of adaptive tracking architectures and, for the first time, identify it as a directly exploitable new attack surface. This insight reveals a previously overlooked and highly vulnerable topological path space attack surface. Based on this, we propose the
Adversarial Path-Inversion (API) framework. API generates imperceptible perturbations to precisely manipulate the gating decisions, forcing the inference onto altered computational paths. The severe inconsistency between the original and the inverted paths dismantles the representation capability of the model. Extensive experiments on state-of-the-art adaptive trackers demonstrate that API achieves superior perturbation stealthiness, more effective attack, and faster inference speeds. This work opens a new dimension for the security analysis of dynamic tracking networks and provides a theoretical warning for constructing robust adaptive tracking architectures in the future.
Read the full abstract ▾
All authors Shaofeng Liang, Runwei Guan, Wenshuo Chen, Jiemin Wu, Bowen Tian, Haozhe Jia, Kaishen Yuan, Songning Lai, Daizong Liu, Yutao Yue
Artificial Intelligence
Intertemporal Preference Steering in Qwen3 via Contrastive Activation Addition
Michal Mráz and Justin Shenk
We study linear representations of temporal horizon in the large
language model Qwen3-32B and use them to change the model's time-related preferences, recommendations, and capabilities. We train contrastive linear probes on teacher-forced temporal-choice answers to find a short-term versus long-term direction in the model's residual stream, and evaluate contrastive activation-addition steering on a held-out binary temporal-choice task, an out-of-distribution monetary intertemporal-choice task, and a TravelPlanner capability
benchmark. The central result is that temporal-horizon directions can be identified with simple contrastive linear probes and then used for steering to induce large, bidirectional preference changes. On an out-of-distribution monetary choice task that varies reward size and delay, steering strongly shifts the model's indifference threshold between smaller-sooner and larger-later rewards in both directions. We further show improvements on a planning-related capability metric under moderate temporal steering. These results suggest that model intertemporal preferences are measurable and steerable, which is relevant for AI systems that give advice involving delayed costs and benefits, and for safety questions about long-horizon planning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel et al. (+8 more)
A clinically useful chest X-ray system must go beyond fluent report generation: it should classify findings with tunable decision thresholds, localize them spatially, and derive the anatomical measurements upon which many diagnoses depend. Today's
Vision-
Language Models (VLMs) treat these as separate problems, if they address them at all, leaving a gap between what radiologists need and what generative models provide. We introduce CARE-X, a chest X-ray VLM that narrows this gap by unifying auxiliary discriminative supervision with reward-aligned generation. CARE-X augments its generative backbone with focal-loss classification and composite-loss grounding heads, co-trained alongside the
language-modeling objective. This auxiliary supervision produces discriminative diagnostic predictions with tunable decision thresholds and precise spatial localization while also improving report quality, providing evidence that structured prediction and generation reinforce one another. Building on this foundation, Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) leverages task-specific reward signals for report generation, visual question answering (VQA), and spatial grounding, directly optimizing the clinical quality metrics that matter in practice. The result is state-of-the-art performance on the majority of metrics across four report-generation
benchmarks, 94.0% VQA accuracy on ReXVQA (+6.0 pp over the next-best baseline), and generative spatial decoding that reaches near parity with dedicated detection heads. Separately, to address measurement-dependent diagnoses, we couple Qwen3-VL-4B-Instruct with native tool-calling capabilities for invoking deterministic measurement tools, while retaining full visual access to the image. This hybrid inference yields +43.6 pp average F1 over perception-only baselines across five measurement-dependent conditions.
Read the full abstract ▾
All authors Mercy Prasanna Ranjit, Anirban Porya, Sathvik Joel, Niharika Vadlamudi, Nikhilesh Chowdary Eathamukkala, Prasanth V V, Abhyuday Kumara Swamy, Pranay Narhari Umredkar, Pradeep Narayan, Vivek Rajagopal, Tanuja Ganu
Artificial Intelligence · Cross-listed from cs.CL
Martin Böckling, Elizaveta Nosova, Heiko Paulheim et al. (+1 more)
Geospatial
reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to
navigation and logistics, yet large
language models (LLMs) struggle with the required
geometric and topological computation despite storing considerable geographic knowledge. Existing
benchmarks localize these failures only partially: they are synthetic or smallscale, largely monolingual, and offer limited control over geographic coverage. We introduce MultiGlobeQA, a
multilingual benchmark of 46,060 question-answer pairs spanning 14 spatial-function families and 15 answer formats, with execution-based ground truth over three knowledge graphs. It covers 201 countries and territories via income- and density-stratified sampling, with parallel questions in English and 16 additional high- and low-resource
languages. Across parametric,
reasoning, and agentic settings, LLMs collapse on tasks requiring grid indexing and shape computation, while topological relations and directions fare best.
Retrieval and tool use yield considerable gains, yet performance plateaus below two thirds even when gold facts are supplied, indicating that computation, not access to knowledge, is the bottleneck. Models also underperform on low-income regions, a gap that gold facts widen rather than close.
Read the full abstract ▾
All authors Martin Böckling, Elizaveta Nosova, Heiko Paulheim, Andreea Iana
Artificial Intelligence · Cross-listed from cs.LG
Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning
Pyrros Koussios, Chenhao Li, Xin Chen et al. (+1 more)
Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL). Recent work uses large foundation
Vision-
Language Models (VLMs) as reward models, computing text-observation similarity to bypass manual reward engineering. Although promising, these rewards are often noisy and unreliable, limiting their direct utility during deployment. We present Structure-Aware Fine-Tuning (SAFT), a simple, self-supervised method that refines these imperfect reward signals online without access to ground-truth supervision. SAFT leverages intrinsic structural priors to regularize the VLM's latent space via LoRA adapters. We rigorously evaluate SAFT across a spectrum of base model capabilities to demonstrate its versatility. Our results show that SAFT consistently denoises the reward landscape, yielding faster policy convergence and substantially improved
alignment (EPIC distance) relative to the underlying base model, suggesting that failures can often be attributed to structural brittleness rather than semantic misunderstanding. By replacing extensive human preference annotation with structural inductive biases inherent to the task, SAFT offers a scalable path for stabilizing text-conditioned RL and underscores the broader value of incorporating task structure as a general inductive bias.
Read the full abstract ▾
All authors Pyrros Koussios, Chenhao Li, Xin Chen, Andreas Krause
Artificial Intelligence
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
Tianyi Guan, Yiding Wang, Haotong Yang et al. (+5 more)
Modern
agent frameworks equip large
language models with external skill libraries to solve complex tasks. However, it remains unclear whether these systems can effectively evolve their skills and whether the resulting skills improve task-solving capabilities. To bridge this gap, we introduce ContinualSkillBench, a dynamic evaluation framework for in-context continual skill learning. It covers five domains, each with 100 tasks ordered by difficulty and opportunities for skill transfer. Our experiments show that sequential execution generally improves performance, but the gains vary substantially across models and domains. Moreover, across two models and three domains, retaining context and feedback without skill maintenance yields nearly the same mean performance as maintaining an explicit skill library. Explicit skills nevertheless provide selective benefits for tasks requiring reusable procedures or precise outputs. We further find that the weaker model (GPT-4o) accumulates more skills but reuses them less often, suggesting difficulty consolidating task-specific experience into reusable procedures. These findings show that current in-context skill
evolution mechanisms can support continual adaptation, but still struggle to consistently consolidate experience into robust and transferable skills.
Read the full abstract ▾
All authors Tianyi Guan, Yiding Wang, Haotong Yang, Siyuan Cao, Shirui Liu, Yi Hu, Jiaqi Li, Muhan Zhang
Artificial Intelligence · Cross-listed from cs.LG
GENESIS: Towards Explainable Causal Discovery
Abhinav Thorat, Ravi Kumar Kolla, Vishak K Bhat et al. (+2 more)
Causal Discovery (CD) from observational data faces two fundamental challenges. First, purely statistical methods often lack the power to resolve structural ambiguities in low-sample regimes. Second, although LLM-assisted hybrid approaches improve structure recovery through semantic
reasoning, the influence of that
reasoning on individual edge decisions remains largely opaque. Consequently, existing hybrid methods fail to satisfy a fundamental requirement: explaining why a particular edge is included or excluded in the learned directed acyclic graph (DAG). This is critical in real-world applications, where no ground-truth DAG exists and every structural decision must be independently justified. We formalize this requirement as decision traceability, requiring every inferred edge to be supported by auditable statistical evidence, Markov Blanket consistency, or explicit domain
reasoning. We propose GENESIS, an explainable hybrid CD framework that decomposes graph construction into interpretable decision points. GENESIS first identifies and scores three-node structural motifs, including chains, forks, and
colliders, to establish transparent structural priors, then progressively refines the graph by integrating these priors with observational evidence, invoking domain knowledge only when statistical evidence is insufficient. By design, every edge decision is resolved through an auditable source of evidence. Experiments show that GENESIS achieves 100% decision traceability across all settings, establishing explainability as a first-class objective in causal discovery. Despite this additional requirement, GENESIS consistently outperforms purely statistical CD methods on the majority of
benchmark datasets across all sample regimes in terms of Structural Hamming Distance (SHD), while achieving performance comparable to state-of-the-art LLM-assisted approaches.
Read the full abstract ▾
All authors Abhinav Thorat, Ravi Kumar Kolla, Vishak K Bhat, Harsh Vardhan Singh Chauhan, Niranjan Pedanekar
Artificial Intelligence
ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories
Yash Misra, Javal Vyas, Siddharth Gutta et al. (+1 more)
This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework implements a versioned, safety-governed evaluation contract that checks whether a recommendation is supported by the available evidence, permitted under the stated authority and procedure, and acceptable under the plant-specific consequence checks encoded in the selected evaluation profile. In this report, safety-governed means that eligibility is determined through explicit, non-compensatory checks derived from a versioned plant profile; it does not mean that the evaluator, model, or plant has been safety-certified. Release 0.1.0 is a public reference implementation for technical and research evaluation, not an authorisation for physical execution.
Read the full abstract ▾
All authors Yash Misra, Javal Vyas, Siddharth Gutta, Mehmet Mercangöz
Artificial Intelligence · Cross-listed from cs.CL
SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAG
Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab et al. (+1 more)
We introduce SciRet, a compute-aware empirical study of
retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense
retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid
retrieval is more robust than either sparse-only or dense-only
retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup.
Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a
benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.
Read the full abstract ▾
All authors Kaysarul Anas Apurba, Md. Hasibul Hasan, Rofiqul Alam Shehab, Asab Azad
Artificial Intelligence · Cross-listed from cs.CL
Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
Peijia Guo, Wenxuan Xie, ZiGuang Li et al. (+1 more)
Large
language models (LLMs) pose challenges to academic integrity and peer review. Yet generative plagiarism detection remains an underexplored and largely unresolved challenge. Prior work on LLM-generated-text detection targets AI involvement, which may be permissible, rather than source reuse, while similarity-based methods struggle after extensive rewriting and multi-source synthesis. Motivated by the description-length view of probabilistic prediction, in which relevant side information can reduce a target sequence's code length, we introduce Source-Conditioned Description-Length Gain (SCDG), a directional, training-free framework that contrasts a frozen
language model's description length of a suspicious document $P$ with and without a candidate source $S$. This contrast yields
token-level log-likelihood gains that measure the incremental predictive evidence supplied by $S$. We evaluate SCDG on the PAN at CLEF
benchmarks for generative plagiarism. On a PAN 2025-derived pairwise
benchmark, SCDG achieves 0.92 Precision, 0.97 Recall, and 0.94 F1, outperforming all baselines; on PAN 2026's multi-source
retrieval task, it reaches 0.83 nDCG@10 and 0.96 Recall@100, surpassing all baselines. On a same-topic, same-event Multi-News test, the calibrated gain-distribution SCDG classifier predicts source reuse for only $0.125\%$ of pairs, supporting robustness to topical overlap under this evaluation protocol. These results establish SCDG as a unified and
token-decomposable signal for source-specific content reuse under extensive transformation.
Read the full abstract ▾
All authors Peijia Guo, Wenxuan Xie, ZiGuang Li, Ming Li
Artificial Intelligence
MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM Agents
Jiaming Chen, Yisen Gao, Yanping Li et al. (+3 more)
Memory-augmented LLM
agents rely on rich context for long-horizon
reasoning and acting, yet their
memory modules expose a persistent attack surface for malicious records, making the study of
memory poisoning threats imperative. However, existing query-only attacks often fail to remain effective in two realistic and prevalent settings: large-scale benign
memory pools and active input
auditing. Consequently, current approaches fall short when facing the dual challenges of high
retrieval competitiveness and rigorous semantic checks. To overcome these limitations, we propose MAFIA, a query-only
Memory Attack framework via probing and Factual Injection against Audit, tailored to this extended threat model. Specifically, MAFIA introduces: (1) a placement strategy that ensures
retrieval-competitive injection via
memory probing, budget allocation, and scheduling; and (2) a payload design that bypasses audits using compact factual cloaks, preserving malicious effects while maintaining high semantic similarity. Extensive evaluations reveal that MAFIA achieves up to a 90.7% attack success rate while suppressing audit detection from a peak of 83.3% to at most 7.4%, exposing critical vulnerabilities across agentic
memory systems. Code will be made publicly available at https://github.com/JiamingChen1234/MAFIA.
Read the full abstract ▾
All authors Jiaming Chen, Yisen Gao, Yanping Li, Zifan Liu, Yumeng Zhang, Jun Zhang