Artificial Intelligence
Ask the World Before Acting: Environment Probing for Calibrating Agent World Models
Xinyuan Song and Zekun Cai
Long-horizon
language agents enable autonomous decision-making in complex environments by planning and executing sequences of interdependent actions. To act reliably, these
agents must maintain an accurate world model that tracks the environment's evolving state and supports subsequent decisions. However, as interactions accumulate, stored beliefs can become outdated or incorrect, causing
agents to plan and act on assumptions that no longer reflect the environment. Such errors are difficult to resolve through additional
reasoning or self-reflection alone, because the information needed for correction must be obtained from the environment. Actively probing the environment therefore offers a direct way to verify and correct these beliefs. To this end, we introduce ENVPROBE, a framework that enables
agents to actively explore their environments and correct inaccurate beliefs during long-horizon execution. Specifically, ENVPROBE prioritizes belief fields for verification based on task relevance and potential errors. It then selectively probes the environment to retrieve the actual value of a chosen field and incorporates the observation into the
agent's world model. With the updated beliefs, the
agent revises its plan and continues execution based on the newly acquired environmental information. Extensive experiments across three controlled environments demonstrate that ENVPROBE substantially improves terminal world-state accuracy compared with
agents operating without environment probing, leading to more reliable long-horizon decision-making. These results demonstrate the importance of actively verifying and correcting beliefs through environmental interactions for maintaining accurate world models in long-horizon
language agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors
Karam Tomotaki-Dawoud, Anna Hilsmann, Peter Eisert et al. (+1 more)
Single-stage
video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached. We address this from two complementary directions: first, we propose TemporalLens, a model-agnostic diagnostic framework probing temporal dependence through controlled perturbations, structured occlusions, temporal shuffling, redundancy injection, and resolution degradation, revealing whether a detector actually uses information across time. Applied to stacked-frame 2D detectors and our YOLO-3D architecture, it exposes behavioural differences invisible to mAP: stacked 2D models collapse when the target frame is removed, while spatiotemporal models recover predictions from earlier frames, a signature of real temporal reliance. Second, we detail YOLO-3D, a modular real-time spatiotemporal detector built on YOLOv8, and show that simply preserving temporal depth through the backbone is the dominant performance driver (+3.7 pp mAP@50 at 32 frames averaged across scales). Together, the diagnostics and architecture turn "does this detector reason over time?" into a measurable, actionable question.
Read the full abstract ▾
All authors Karam Tomotaki-Dawoud, Anna Hilsmann, Peter Eisert, Sebastian Bosse
Artificial Intelligence
BP-TTA: Balanced and Prototype-Guided Test-Time Adaptation in Dynamic Scenarios
Shaoyang Huang, Yashi Zhu, Yichen Yu et al. (+3 more)
Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts. While recent TTA methods have moved beyond static settings and begun to consider continual domain shifts, they primarily address distribution drift and fail to account for class imbalance in dynamic scenarios. In real-world test-time streams, class imbalance and continual domain shifts often occur at the same time and interact with each other. In this paper, we propose a novel Balanced and Prototype-Guided Test-Time Adaptation (BP-TTA) method, which combines batch-balanced sampling with prototype-guided adaptation to handle the class imbalance and continual domain shift problems. BP-TTA constructs balanced adaptation batches by integrating current samples with high-confidence historical instances, effectively mitigating bias toward dominant classes and stabilizing online updates. Meanwhile, BP-TTA maintains evolving class prototypes during inference and leverages prototype similarity as a constraint for model adaptation, thereby improving the reliability of pseudo-labels and enhancing the stability of online updates under persistent domain shifts. Extensive experiments demonstrate that BP-TTA consistently outperforms state-of-the-art TTA methods in dynamic test-time streaming settings.
Read the full abstract ▾
All authors Shaoyang Huang, Yashi Zhu, Yichen Yu, Lei Zhang, Zhang Yi, Tao He
Artificial Intelligence
Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs
Seyed Alireza Molavi, Zhan Su, Yan Hu et al. (+3 more)
Composing independently trained LoRA adapters into a single large
language model is useful for multi-domain adaptation, especially when the original training data cannot be shared. A common approach is to use MoE-style routing over LoRA experts, but for frozen pretrained adapters, soft weighted combinations can change the unit-scale additive update under which each LoRA module was originally trained. We propose Hard-Routed MoR-LoRA, a two-stage framework for composing frozen
reasoning LoRA experts through unit-scale hard selection. First, domain-specific LoRA adapters are trained independently using reinforcement learning from verifiable feedback to obtain
reasoning experts. Then, all experts are frozen,
reasoning traces are distilled from them, and only a lightweight shared router together with a small
attention LoRA is trained for integration. The router selects exactly one expert per
token using hard top-1 routing, while a straight-through
estimator enables gradient-based training. Experiments across five
benchmarks, multiple model scales, and additional model families show that Hard-Routed MoR-LoRA preserves expert behavior while requiring substantially fewer trainable parameters than soft-routing mixture baselines. Our analysis further shows that normalized soft mixtures often concentrate most routing mass on a single expert, suggesting that hard unit-scale routing provides a simple and efficient abstraction for frozen LoRA expert composition.
Read the full abstract ▾
All authors Seyed Alireza Molavi, Zhan Su, Yan Hu, Peyman Sheikholharam Mashhadi, Stefan Byttner, Prayag Tiwari
Artificial Intelligence
Xiaomi-GUI-0 Technical Report
Wanxia Cao, Chengzhen Duan, Pei Fu et al. (+29 more)
Graphical user interface (GUI)
agents build on
vision-
language models to complete user tasks end-to-end in real applications through interface actions such as tapping, swiping, text entry, and
navigation. However, existing GUI
agents are trained and evaluated largely on offline trajectories, simulated environments, and standardized
benchmarks. These differ substantially from real applications in interface layout, interaction logic, and abnormal-state distribution, and cannot faithfully characterize execution stability in real-world use, where account states, permission dialogs, payment authentication, and risk control continually reshape the state distribution and open a persistent gap between
benchmark scores and real usability. To close this gap, we propose Xiaomi-GUI-0, a native
multimodal GUI
agent for real mobile environments, trained and evaluated within a real-device closed loop. At its core is a real-device-dominant hybrid infrastructure, where physical devices are the primary execution environment and sandboxes provide auxiliary support, so that data collection, training, rollout, and evaluation share an execution distribution close to real deployment. We construct multi-source training data spanning high-frequency head tasks, high-generalization data for long-tail intents, and capability-enhancement data for reflection and
memory, and introduce an error-driven data flywheel that turns failure trajectories into corrected actions, reflective explanations, and recovery demonstrations. The model is trained through a progressive three-stage pipeline of supervised fine-tuning, step-level reinforcement learning, and agentic reinforcement learning. Evaluated on public
benchmarks and our in-house RealMobile, Xiaomi-GUI-0 achieves 72.0% success on RealMobile and 78.9% on AndroidWorld, while substantially improving execution stability and abnormal-state recognition in real-world tasks.
Read the full abstract ▾
All authors Wanxia Cao, Chengzhen Duan, Pei Fu, Pengzhi Gao, Niu Lian, Fazhan Liu, Hui Liu, Heng Qu, Qinzhuo Wu, Zhehao Yu, Tongbo Chen, Shiqi Cui, Anan Du, Shukai Jia, Yuanfa Li, Wei Liu, Yike Liu, Wenchao Lu, Zhenbo Luo, Haoyuan Sun, Jiatong Sun, Cheng Tan, Yajie Wang, Changqiao Wu, Tao Xiong, Jiahui Yang, Yuxuan Yuan, Ruoceng Zhang, Shaojie Zhang, Jian Zhu, Jian Luan, Cong Zou
Artificial Intelligence · Cross-listed from cs.CV
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
Ta Duc Huy, Trang Nguyen, Townim Chowdhury et al. (+5 more)
Vision-
language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common
entropy-based methods, such as Semantic
Entropy (SE), rely on output diversity. Yet our analysis shows that overconfident visual
embeddings suppress output diversity under
stochastic decoding, causing SE to underestimate uncertainty in such cases. Recent methods instead probe output diversity through input perturbations, including textual paraphrasing or joint text-image perturbations, and show improved performance. We study these approaches and reveals that the resulting variability is often dominated by textual changes rather than visual evidence, causing uncertainty estimates to reflect
prompt sensitivity rather than visual ambiguity. We therefore propose Visual Semantic
Entropy (VSE), which perturbs only the image to probe nearby visual variations while keeping the text query fixed. VSE measures uncertainty by clustering generated answers into semantic prototypes and computing the mass-weighted dispersion among them. Extensive evaluation across five modern
vision-
language models and five diverse VQA
benchmarks demonstrates that VSE effectively captures visual ambiguity, establishing a new state-of-the-art for VLM uncertainty estimation.
Read the full abstract ▾
All authors Ta Duc Huy, Trang Nguyen, Townim Chowdhury, Ankit Yadav, Minh-Son To, Zhibin Liao, Johan W. Verjans, Vu Minh Hieu Phan
Artificial Intelligence
Wisdom Of The (AI) Crowd: Investigating Artificial Swarm Intelligence In Large Language Models
Justin Brenne and Christian Meske
Human swarm intelligence demonstrates remarkable collective accuracy but faces scalability constraints in cost, coordination, and time. We investigate whether large
language models (LLMs) can approximate swarm intelligence effects through artificial swarms, addressing a critical gap in understanding AI-based aggregation mechanisms. We conducted a controlled experiment with 960 manually executed
prompts across three proprietary models (GPT-5, Gemini 2.5 Pro, Claude Sonnet 4.5), testing intra-model sampling and inter-model aggregation on eight estimation tasks. Results reveal consistent error reduction through intra- and inter-model aggregation, with significant error reductions up to 37 percentage points in MAPE across different aggregation strategies. We observed small to large effect sizes for positive correlations (Spearman's $\rho=0.242-0.568$, all $p<0.001$) between relative confidence interval widths and relative estimation errors, suggesting LLMs possess metacognitive awareness when assessing uncertainty. We discuss implications for research and practice, providing actionable insights for deploying LLM swarms in organizational decision-making.
Read the full abstract ▾
Artificial Intelligence
World-Model Collapse as a Phase Transition
Xinyuan Song and Zekun Cai
Water looks unchanged as it warms, then at a critical point it boils. We ask whether long-horizon
language agents show an analogous transition in their implicit world models. In some parameter settings, changing state load by a small amount, or adding a single step of horizon, leaves behavior nearly unchanged; near a critical boundary, the same small change causes a sudden world collapse. We study this effect in a deterministic task family with exact per-step gold state. A large grid search over state cardinality, dependency density, horizon, branching, observation mode, and mutation rate reveals a phase diagram: a solved plateau, a narrow transition band, and a collapse floor. Per-step traces show the mechanism: world-state fidelity fails before action validity, so the
agent is not merely choosing a bad action; it is acting from a corrupted world. Stronger models translate the critical boundary but do not remove the qualitative transition. These results make world-model collapse a measurable bottleneck for long-horizon
agents.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models
Duc Anh Nguyen, Tien Ngoc Luu, Tung Pham et al. (+1 more)
State-based fine-tuning has emerged as a compelling alternative to weight-based adaptation for
transformers, updating lightweight controls into states rather than model weights, offering substantial
memory savings while retaining parameter efficiency. However, most existing state-based methods typically apply only per-block control updates, which limits inter-block information exchange and restricts representational adaptation. Meanwhile, prior mechanisms that enable cross-block communication often introduce considerable computational overhead, reducing their practicality for efficient fine-tuning. We introduce Mixture-of-Control (MoC), an efficient cross-layer communication that adaptively integrates local and global control signals to enhance representation learning during adaptation. MoC treats block-wise control states as experts in a sparse mixture-of-experts process, enabling efficient communication across
transformer blocks. Experiments on 33
datasets and 10 pretrained models across diverse
transformer-based
benchmarks demonstrate that MoC consistently outperforms existing state-based fine-tuning methods while maintaining comparable efficiency in
memory and compute.
Read the full abstract ▾
All authors Duc Anh Nguyen, Tien Ngoc Luu, Tung Pham, Toan Tran
Artificial Intelligence · Cross-listed from cs.LG
Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images
Jisung Park, Seohyeon Kang, Daeun Yoo et al. (+8 more)
Artificial intelligence is transforming our capability to solve biological challenges. In dimensionality bottleneck regimes exacerbated by high-dimensional biological data, neural networks force distinct concepts into the lower dimensions known as superposition. Although this superposition is widely known to hinder interpretability, its impact on corrupting the geometry of latent spaces remains critically overlooked. Here, we utilized sparse autoencoders (SAEs) trained on over 100,000 multiplexed images of patient-derived Parkinson's disease and healthy
neurons to resolve superposition. This approach bypasses the mathematical non-uniqueness of feature attribution by shifting to interpretable latent representation analysis. We theoretically and empirically demonstrate that superposition contaminates representational metric spaces, and thereby SAEs successfully recover
geometric fidelity. By treating these geometrically purified representations as single-
cell state vectors, we adapted single-
cell RNA sequencing (scRNA-seq) data analysis methodologies directly to the image domain. Finally, we introduce GW-map, utilizing Gromov-Wasserstein optimal transport to align these image representations with authentic scRNA-seq data de novo. This coupling reconstructs hierarchical neuronal pathology pathways such as Calcium-AIS scaffold, without reference spatial transcriptomics, establishing a scalable foundation for spatial biology. Code is available at https://github.com/jijihihi/Bio\_superposition
Read the full abstract ▾
All authors Jisung Park, Seohyeon Kang, Daeun Yoo, Eunsu Lee, Seoin Cho, Wooyeop Choi, Ian Choi, James R. Evan, Daesoo Kim, Sonia Gandhi, Minee L. Choi
Artificial Intelligence
ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents
Binjie Zhang and Mike Zheng Shou
Tool-augmented
vision-
language models (VLMs) can solve
multimodal, multi-step tasks by calling external tools, yet they remain fragile in practice. Existing works have two common gaps. Supervised fine-tuning (SFT) is built mostly on successful trajectories and offers little signal for recovery after tool failures, while sparse trajectory-level RL rewards provide limited guidance on which step failed and how to repair it. We introduce ReGRPO (Reflection-augmented Group Relative Policy Optimization), a framework that learns reflection-guided correction in tool-using
agents. ReGRPO starts with a structured reflective data engine: we execute near-miss actions to collect grounded failure observations, then build Reflection-of-Thought triplets (ErrorType, Evidence, FixPlan) paired with corrected actions for warm-start SFT. We then optimize reflection
tokens and corrective actions jointly within local trajectories using group-relative advantages, and include a reflection-cost term to reduce unnecessary reflection. Experiments on GTA and
GAIA show that, under the same backbone and tool suite, ReGRPO consistently outperforms strong open-source baselines and achieves the best results among the compared open-source controllers. Code and RoT data are available at https://github.com/showlab/ReGRPO.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Stage-Transition Dense Reward Modeling for Reinforcement Learning
Yang Yang, Bingjie Chen, Zihan Wang et al. (+4 more)
Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to changes in environments and object configurations. This work proposes Stage-Transition Dense Reward (STDR), a visual reward-learning framework that converts unstructured expert
videos into logically grounded dense rewards for training RL
agents from scratch. STDR leverages semantic understanding to infer a task's stage structure from demonstrations, and delivers two complementary learning signals during online training: (i) stage-transition feedback that provides goal-directed reward, and (ii) within-stage progress feedback that supplies fine-grained guidance toward completing each stage. Furthermore, an out-of-distribution (OOD) detection mechanism and a grasping regulation module are integrated to enhance robustness and prevent reward hacking. Experiments on 14 manipulation tasks across MetaWorld, ManiSkill, and Franka Kitchen show that STDR consistently improves sample efficiency and success rates over multiple baselines, and matches or surpasses handcrafted dense rewards on several challenging tasks. Real-
robot evaluations further indicate that STDR assigns stable, progress-aligned rewards on successful executions while producing appropriately low rewards for failures, suggesting robustness to visual noise and better-calibrated reward assignment across settings.
Read the full abstract ▾
All authors Yang Yang, Bingjie Chen, Zihan Wang, Yizhe Li, Guoping Pan, Yi Cheng, Houde Liu
Artificial Intelligence · Cross-listed from cs.LG
Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?
Zewen Liu
When large
language model (LLM)
agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the
agent's learned strategy distribution - a phenomenon termed evaluator preference coupling. Prior work has documented this coupling and established a diagnostic framework (EPC) to measure it, but has not investigated whether calibration techniques can mitigate the effect. We present the first study of evaluator calibration as mitigation: applying probability calibration to the evaluator's pairwise judgments to reduce spurious preference propagation. In a controlled within-subjects experiment (N=5) comparing standard binary TTRL (win/loss) with confidence-calibrated TTRL (probability-weighted updates) using DeepSeek-V4-Pro as executor and GLM5.2 as evaluator, we find that calibration reduces the coupling coefficient gamma by 20-49% and Jensen-Shannon divergence by 45-67%. A symmetric-LR control confirms the effect is not due to reduced update asymmetry. We release the calibrated TTRL protocol and recommend it as a lightweight mitigation for LLM-as-judge deployment pipelines.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
From Materials Database to Materials Bank: Assetizing Data for AI Driven Materials Innovation
Chenyao Ma, Di Zhang, Weibo Gong et al. (+9 more)
Driven by high-throughput experimentation, computational modeling, and artificial intelligence (AI), materials data has expanded at an unprecedented rate. Conventional materials databases function only as passive repositories, archiving raw experimental records indiscriminately including both successful and failed data, without systematic value filtering or asset management. This creates a critical gap between massive data accumulation and actionable innovation, hindering the identification of high-potential materials and industrial translation. To address this bottleneck, we propose an industrialization-oriented Materials Bank, a dedicated valuefiltering and assetization layer that operates beyond traditional databases. It does not merely curate high-quality data but systematically elevates qualified candidates into standardized, upgradable materials assets via a multi-dimensional BankCard framework covering scientific validity, synthesis feasibility, application readiness, and industrial value. By unifying databases, AI models, automated experimentation, and multi-criteria assessment into a cohesive closed-loop ecosystem, the Materials Bank establishes a clear trajectory from data to knowledge, candidate, asset, and product. It serves not as an enhanced database or screening tool, but as a decision infrastructure bridging academic discovery and industrial demand, offering a scalable paradigm to accelerate AI-driven materials innovation and deliver tangible real-world impact.
Read the full abstract ▾
All authors Chenyao Ma, Di Zhang, Weibo Gong, Wei Du, Rui Su, Yuhang Chen, Kan Xu, Huan Gu, Limin Li, Piao Ma, Zhenghao Li, Hao Li
Artificial Intelligence · Cross-listed from eess.SP
PGUDA: Pressure-Guided Unsupervised Domain Adaptation with Cross-Modal Knowledge Distillation for sEMG-Based Gesture Recognition
Yurui Liu, Xiao-Cong Zhong, Qisong Wang et al. (+3 more)
Surface electromyography (sEMG)-based gesture recognition has emerged as a promising technology for natural human-computer interaction. However, its practical deployment remains challenging due to severe performance degradation caused by feature distribution discrepancies across different subjects and recording sessions. Although domain adaptation (DA) techniques are commonly employed to mitigate such discrepancies, conventional methods often struggle to effectively aligning sEMG features, primarily due to their inherent stochasticity and the scarcity of labeled data. To address these limitations, this paper proposes a novel Pressure-Guided Unsupervised Domain Adaptation (PGUDA) framework, which leverages the robustness and stability of pressure signals to introduce a cross-modal knowledge
distillation strategy that transfers consistent physical semantics across modalities. Specifically, a teacher network trained on pressure signals guides an sEMG student network on unlabeled target domains, thereby regularizing the representation learning process with transferable and modality-invariant knowledge. Extensive experiments conducted on a self-collected
multimodal dataset involving eleven subjects validate the effectiveness of the proposed PGUDA framework. The results demonstrate that our proposed PGUDA achieves leading performance in both cross-subject and cross-session classification tasks, achieving average accuracies of 58.08% and substantially outperforming existing DA approaches. Notably, PGUDA exhibits remarkable label efficiency: it attains classification accuracy comparable to fully supervised
benchmarks while requiring only 5% of labeled data for teacher network training. This framework offers a robust and data-efficient solution that can significantly reduce the calibration burden in practical sEMG-based gesture recognition systems.
Read the full abstract ▾
All authors Yurui Liu, Xiao-Cong Zhong, Qisong Wang, Xuefu Wang, Dan Liu, Jinwei Sun
Artificial Intelligence
Smart charging of large fleets of Electric Vehicles: Independent Multi-Agent Reinforcement Learning approaches
Xavier Rate, Eloann Le Guern, Raphaël Féraud et al. (+8 more)
The electrification of transportation through electric vehicles introduces new challenges for power grid management, such as increased peak demand, voltage fluctuations, line overloads, and the integration of variable renewable energy sources. To enable efficient integration of EVs while minimizing costs for users and avoiding network overloads, implicit coordination between EVs is required. This work compares two independent multi-
agent reinforcement learning approaches for optimizing such decentralized EV charging: contextual combinatorial bandits and policy gradient
algorithms. Using a realistic simulation environment with autonomous
agents making decisions based on local environmental information (including price signals, state-of-charge, and temporal constraints), we evaluate their performance across varying congestion levels, and mixed-strategy configurations with heterogeneous
agent groups under dynamic electricity pricing derived from real photovoltaic production data.
Read the full abstract ▾
All authors Xavier Rate, Eloann Le Guern, Raphaël Féraud, Fatma Salem, Melissa Chiknoun, Eymeric Giabicani, Mehdi Feki, Patrick Maillé, Guy Camilleri, Anne Blavette, Hamid Benhamed
Artificial Intelligence · Cross-listed from cs.SD
Beyond Binary Instrument QA: Probing Instrument Grounding in Music Audio-Language Models
Yujun Lee, Joonhyeok Shin, Hyoeun Kim et al. (+1 more)
Recent music audio-
language models achieve high accuracy on instrument question-answering
benchmarks, but it remains unclear whether this reflects robust audio grounding or
benchmark-specific shortcuts. In this paper, we introduce an OpenMIC-derived diagnostic
benchmark sequence for instrument grounding in music audio-
language models, extending binary instrument-presence QA to genre-prior-reduced examples, confusable instrument discrimination, longer audio context, and temporal localization. Across these settings, high binary QA accuracy often fails to predict model behavior: models can exhibit option-position bias, confusable-instrument errors, and temporal response bias. These results suggest that instrument grounding should be evaluated with multi-axis diagnostic
benchmarks rather than a single aggregate accuracy.
Read the full abstract ▾
All authors Yujun Lee, Joonhyeok Shin, Hyoeun Kim, Kyuhong Shim
Artificial Intelligence
Optimization Algorithms for Joint OFDM Waveform Design and RIS Configuration in 6G Networks: From Convex Relaxation to Foundation Models
Ahmet Kaplan
Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min
fairness, and peak-to-average power ratio (PAPR)-constrained objectives. Seventy-eight joint OFDM-RIS optimization works published between 2021 and 2026 are surveyed. No standardized
benchmark exists, and cross-paper comparisons remain infeasible. This survey classifies these works into four paradigms: (I) model-based convex relaxation, (II) heuristic and metaheuristic search, (III) deep reinforcement and unsupervised learning, and (IV) emerging methods including foundation models (FM),
diffusion-based generative AI, and
quantum optimization. A literature synthesis of self-reported
benchmarks shows that ML-based methods (Paradigm~III) report 95-99% of model-based spectral efficiency at 10^2-10^4 x faster per-inference runtime (method-pair dependent; literature values are self-reported and exclude ML pre-training cost). A companion tutorial
benchmark at N=16, N=64, and N=128 reveals a critical scaling property: GPU-based neural network inference (DDQN, PPO, graph neural network (GNN), unsupervised DL) is N-invariant, with identical runtime at N=16 and N=128, while iterative solvers (AO+SCA, PSO) scale polynomially. Energy efficiency (P2) and PAPR-constrained (P4)
benchmarks are deferred to future work with standardized power models and waveform generators. Six open challenges emerge from the synthesis: the cross-paradigm
benchmark deficit, real-world hardware-constrained deployment, joint waveform-RIS optimization for doubly-dispersive channels, multi-objective PAPR trade-offs, LLM safety in live network control, and diminishing returns of standalone heuristics. We specify requirements for a standardized
benchmark. This study serves as a roadmap for researchers and practitioners working on joint OFDM-RIS optimization in 6G networks.
Read the full abstract ▾
Artificial Intelligence
CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM
Minzhang Li, Mingrui Li, Weichen Qin et al. (+5 more)
Protein automodeling from cryo-EM density maps faces unique challenges in enforcing physicochemical validity and managing conformational heterogeneity. Current solvers are often limited to static predictions or require computationally intensive heuristic searches. We present CryoACE, an end-to-end framework that reconstructs precise atomic graphs for both homogeneous and heterogeneous structures. Our method features two key innovations: an atom-centric reconstruction paradigm, where density features are sampled directly at atomic coordinates and iteratively recycled to refine structures, replacing expensive voxel convolutions for efficient
multimodal fusion; and a training-free guidance mechanism that leverages predicted local resolution priors to resolve dynamic ambiguity. Validated on a newly constructed high-quality
dataset, CryoACE significantly outperforms existing baselines on static
benchmarks and, for the first time, unveils atomic-level dynamic conformations on complex real-world
datasets like EMPIAR-10345 without relying on pre-built static structures.
Read the full abstract ▾
All authors Minzhang Li, Mingrui Li, Weichen Qin, Qihe Chen, Sixian Shen, Yuan Pei, Jiakai Zhang, Jingyi Yu
Artificial Intelligence · Cross-listed from cs.RO
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Dongyoon Hwang, Byungkun Lee, Dongjin Kim et al. (+7 more)
Hierarchical
Vision-
Language-Action (VLA) models decouple high-level planning from low-level control to improve generalization in
robot manipulation. Recent work in this paradigm uses 2D end-effector trajectories predicted by a
Vision-
Language Model (VLM) as explicit guidance for a downstream policy. However, state-of-the-art low-level policies operate in 3D metric space on point clouds, and feeding them 2D guidance that lacks depth forces each waypoint to be assigned the depth of whatever scene surface lies beneath it, producing geometrically distorted trajectories. We propose 3D HAMSTER, a hierarchical framework that closes this gap by having the planner directly output metrically reliable 3D trajectories. We augment a VLM with a dedicated depth encoder and a dense depth reconstruction objective to predict 3D waypoint sequences, which are directly integrated into a pointcloudbased low-level policy. Across 3D trajectory prediction, simulation, and real-world manipulation, 3D HAMSTER consistently outperforms proprietary VLMs and 2D-guided baselines, with the largest gains under appearance-altering shifts and unseen
language, spatial, and visual conditions. The project page is available at https://davian-robotics.github.io/3D_HAMSTER/.
Read the full abstract ▾
All authors Dongyoon Hwang, Byungkun Lee, Dongjin Kim, Hyojin Jang, Hoiyeong Jin, Jueun Mun, Minho Park, Hojoon Lee, Hyunseung Kim, Jaegul Choo
Artificial Intelligence
HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)
Aurélien Pellet, Julien Perez and Marie Puren
We present HistoriQA-ThirdRepublic: a French-
language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic. Designed in collaboration with a historian, the corpus captures complex
reasoning patterns typical of historical inquiry, including cross-source synthesis, temporal
reasoning, and the integration of sparse evidence. The
dataset is made of 1782 questions and emphasizes multi-hop connections across heterogeneous historical documents, providing a resource for evaluating
retrieval-augmented and large
language model systems in domain-specific contexts. We describe the methodology for constructing the corpus, including the selection and
alignment of sources, question validation, and metadata integration. While the
dataset focuses on French historical documents, our methodology can be readily adapted to other
languages and national corpora. Finally, we demonstrate how the corpus can support realistic evaluation scenarios for multi-hop question answering, bridging the gap between NLP
benchmarks and the needs of historical scholarship.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
From Idea to Prototype in an Afternoon: Scaffolded, AI-Assisted Rapid VA Prototyping
Gennady Andrienko and Natalia Andrienko
Testing a new visual-analytics idea usually takes months: one needs to find a realistic data set, clean it, and implement an interactive prototype. We describe a case where a workflow
language and an AI assistant reduced this effort to one afternoon. The idea under test: relax the Pareto frontier with a tolerance and group the surviving options into recurring types – “constellations” on a “soft sky”. Using the Artifact–Transform Workflow
Language (ATWL) as a scaffold, we obtained a consistent workflow in minutes and a running prototype in a few hours. We derive three lessons. The scaffold matters: without ATWL the assistant produced a naive workflow. The scaffold alone is not enough: the first implementation was only average, and expert knowledge injection was needed to reach state-of-the-art quality. Finally, the way the scaffold is used matters: controlled experiments show that a
language definition and a library of examples support different aspects of the task, that providing both at once reduces quality because template following displaces creative content, and that scaffolds work best when introduced after an initial unconstrained design pass. We argue that the field needs a typology of human knowledge injection, in a form that is both human-editable and machine-accessible.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
Zhengxing Li, David J. Miller, Guangmingmei Yang et al. (+1 more)
While post-training
backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM input space is discrete, with up to 150,000^k k-tuples to consider with k the
token-length of a putative trigger. Second, one must blacklist
tokens typical of the putative target response (class) of an attack, as such
tokens may give false detection signals. However, a comprehensive blacklist is not available, in general, for a given domain. We develop a highly effective detection and inversion framework for LLMs treated as classifiers. Central to our approach is class subspace orthogonalization (CSO), a novel plug-and-play paradigm for
backdoor detection that serves two fundamental roles when applied to LLMs: i) it enhances both sensitivity and specificity of a baseline detector; ii) it provides a form of implicit blacklisting, as it penalizes against inclusion, in a candidate trigger, of
tokens that induce signal perturbations "in the direction of" the putative target class of an attack. One version of our detector performs continuous optimization in
token embedding space, while a companion trigger-inversion and detection method performs greedy
accretion in discrete
token space. Our methods give both strong detection performance and accurate inversion of ground-truth triggers on several LLM classification domains, and for several different LLM architectures.
Read the full abstract ▾
All authors Zhengxing Li, David J. Miller, Guangmingmei Yang, George Kesidis
Artificial Intelligence
Benchmarking Large Language Models on Floating-Point Error Classification
Lisa Taldir, Muhammad Ahmad Saeed, David Defour et al. (+2 more)
This paper investigates the capability of Large
Language Models (LLMs) to detect and classify floating-point errors statically in software code. We introduce InterFLOPBench, a
benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs. The evaluation framework treats floating-point error detection as a multi-label classification problem and employs the F1-score metric to measure performance. Results demonstrate that latest models (Qwen 3 32b, Gemini 2.5 Flash, Phi 4
Reasoning, DeepSeek R1T2, and gpt-oss 20b and 120b) achieve a performance greater than 0.88 overall F1-score. Performance varies between error categories, between explicit operations such as division by zero (Average F1-score: 0.8479) and more subtle numerical phenomena such as underflow (Average F1-score: 0.6059) and cancellation (Average F1-score: 0.6164).
Read the full abstract ▾
All authors Lisa Taldir, Muhammad Ahmad Saeed, David Defour, Pablo de Oliveira Castro, Eric Petit
Artificial Intelligence · Cross-listed from eess.SP
Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications
Huanyu Zhang, Yulin Hu, Xiaopeng Yuan et al. (+2 more)
The emerging techniques of semantic communications and edge computing in 6G networks necessitate a paradigm shift toward co-designed semantic-aware and adaptive resource allocation for short-packet transmissions. However, there is a fundamental gap between the semantic layer and the physical layer under low-latency finite blocklength (FBL) effects. To bridge this gap, we introduce the Quantized Semantic Age of Information (QSAoI), a novel metric that rigorously captures the trade-offs among freshness and semantic efficiency of high-level features in real-time communication in the FBL regime. Guided by this metric, we propose a novel foundation model-based efficient co-designed framework to minimize the expected QSAoI over wireless fading channels in latency-constrained semantic communication. Specifically, we formulate a non-linear joint optimization problem to dynamically optimize the block-wise mixed-precision quantization (MPQ) strategy and the physical blocklength. To efficiently resolve this complex problem, we develop a high-efficiency low-complexity
algorithm based on fixpoint inspection and bisection search. Extensive simulations validate that our proposed
algorithm dynamically adapts the semantic quantization precision to varying channel conditions, effectively minimizing the expected QSAoI compared to baselines.
Read the full abstract ▾
All authors Huanyu Zhang, Yulin Hu, Xiaopeng Yuan, Aydin Sezgin, Anke Schmeink
Artificial Intelligence
Spatial Reasoning via Modality Switching Between Language and Symbolic Representations
Shreya Rajpal, Tanawan Premsri and Parisa Kordjamshidi
Human
reasoning is inherently
multimodal: when problems become difficult, we rarely think in words alone. We often externalize our
reasoning by sketching diagrams or drawing grids to understand the underlying conceptual structure and avoid mistakes. Building on this premise, our research investigates: (a) whether grounding multi-hop textual-spatial stories into geometry-aware modalities, such as layouts or grids, improves
reasoning compared to natural
language-based inference; and (b) whether a model can decide when to rely on natural
language reasoning and when to switch to a structured modality. We address these questions by introducing a switching metric based on trustworthiness and complexity signals, which estimates when grounding a spatial story into structure is likely to improve performance. This takes a first step toward principled modality selection in Large
Language Model (LLM)
reasoning. Across our settings, switching from natural
language-based
reasoning to a grid-based representation improves LLM performance by up to 42%, highlighting the importance of modality choice in shaping
reasoning outcomes.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
Julien Lefebvre, Stefan Duffner and Mathieu Lefort
Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under
memory constraints. Existing methods rely either on replay buffers that exploit latent space structure, or on regularization alone. We present CLIMB (Continual Learning with Intelligent
Memory Bank), which combines both simultaneously. Our method introduces a hierarchical centroid-based
memory, bounded in total number of stored images, combined with knowledge
distillation on replayed examples to limit representation drift. The
memory groups similar images into centroids, providing hard-to-discriminate examples for contrastive learning while covering the diversity of observed distributions. Experiments on Split CIFAR-100 and Split ImageNet-100, on standard
benchmarks from the state-of-the-art as well as a new protocol with irregular task distributions show that CLIMB outperforms state-of-the-art OCSSL methods.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt et al. (+2 more)
Computer-use
agents, which leverage
multimodal large
language models (MLLMs) to operate computers and complete tasks, have attracted significant
attention for their utility and versatility. A major challenge in developing these
agents is collecting large-scale, high-quality trajectories. The standard approach generates synthetic data through a self-improving loop: an
agent is placed in a verifiable environment and iteratively fine-tuned on its successful trajectories. Despite its effectiveness, this paradigm exploits only successful trajectories and discards the failed ones, even though failures carry rich information about a model's weaknesses. In this work, we explore a complementary failure-driven self-improvement loop, a data-centric paradigm that turns failed trajectories into
agent improvements. Specifically, we employ an LLM to diagnose failure modes, propose inference-time solutions, and generate code patches – lightly verified by humans – that upgrade the
agent. We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld
benchmark, improving the success rate from 42.3% to 48.9%, a gain of 6.6 percentage points, without any additional training cost and with only modest inference overhead. Our results demonstrate that failure-driven self-improvement is a viable complement to success-based pipelines, enabling more efficient
agent improvement.
Read the full abstract ▾
All authors Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy, Yuhui Zhang
Artificial Intelligence · Cross-listed from cs.LG
TDGT: A Tabular Data Generation Toolkit supporting adaptive GPU-accelerated Bayesian mixture models, diffusion-based models, and latent-space generative modeling
Vasileios C. Pezoulas, Nikolaos S. Tachos, Eleni Georga et al. (+3 more)
The growing demand for
privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. Despite notable advances in generative modeling, existing solutions often lack integration of adaptive generation strategies, multi-metric evaluation, and accessible end-to-end generators within a unified web-based toolkit. In this work, we introduce TDGT (Tabular Data Generation Toolkit), a web-based toolkit for synthetic tabular data generation and fidelity assessment. TDGT introduces the Adaptive
Bayesian Mixture Synthesizer (ABMS), a novel
algorithm that autonomously determines the optimal number of mixture components through iterative cluster quality optimization, eliminating the need for manual hyperparameter configuration. Building upon ABMS, we further propose VAE-ABMS, a hybrid architecture that couples Variational Autoencoder-based latent space learning with adaptive
Bayesian mixture synthesis, enabling high-fidelity generation of complex, nonlinear tabular distributions. For large-scale scenarios, TDGT provides a GPU-accelerated variant of ABMS leveraging CUDA-based k-means clustering and Gaussian mixture fitting. Synthetic data fidelity is assessed through eleven statistical fidelity metrics spanning distributional divergence, structural correlation, and sample-level similarity, complemented by
privacy risk indicators including k-anonymity scoring and disclosure rate estimation. The web-based toolkit supports a real-time streaming interface with interactive Plotly-based visualizations. TDGT is assessed across
datasets from healthcare, socioeconomic modeling, and cybersecurity domains, demonstrating consistent generation fidelity and statistical coherence across heterogeneous feature types and data scales.
Read the full abstract ▾
All authors Vasileios C. Pezoulas, Nikolaos S. Tachos, Eleni Georga, Kostas Marias, Manolis Tsiknakis, Dimitrios I. Fotiadis
Artificial Intelligence · Cross-listed from cs.SD
SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generation
Binh Mai, Tran Quoc Bao Le, Hung Dinh et al. (+1 more)
Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text–audio data during
distillation. To address these limitations, we propose SwiftAudio, a one-step TTA framework that performs audio-free
distillation from a pretrained
diffusion teacher using only text captions. Specifically, we adapt Variational Score
Distillation (VSD) to the audio domain and introduce a temporal smoothness regularization objective to encourage coherent latent audio representations. This design enables the student model to inherit the teacher's generative prior without requiring paired audio supervision and allows effective training with only approximately 45K captions. Experiments on AudioCaps and Clotho demonstrate that SwiftAudio achieves state-of-the-art performance among strict one-step methods and substantially narrows the gap to multi-step
diffusion systems. Project page: https://swiftaudio.org/
Read the full abstract ▾
All authors Binh Mai, Tran Quoc Bao Le, Hung Dinh, Cong Tran