Artificial Intelligence
When Specifications Conflict: A Symmetry-Based Framework for Measuring LLM Preferences
Tairan Wang, Liang Zhou, Zikang Zhan et al. (+1 more)
Large
language models (LLMs) are increasingly required to integrate multiple sources of information that may be inconsistent or conflicting. However, there is still a lack of controllable and attributable methods for analyzing how models resolve conflicts between competing specifications. We propose a controlled experimental framework for studying model preferences under conflicting specifications. By constructing specifications with explicit conflicts, the framework enables model choices between competing specifications to be directly observed and analyzed. A
symmetry-based design further reduces confounding factors, allowing preferences across representation types to be compared systematically. We evaluate the framework on an executable mathematical
benchmark with 550 conflict instances spanning 11 function families, comparing four representation types: pure natural
language, formal
language, naturalized formal
language, and input–output examples. Results show systematic preference patterns rather than random behavior, with a consistent ordering: $ \text{Formal} \approx \text{Naturalized Formal} > \text{Pure Natural Language} > \text{Input--Output Examples} $. Example effects further depend on model capability and function family. We extend the framework to heterogeneous specification conflicts in Boolean
algebra, code generation, and the clinical domain, demonstrating its applicability across diverse tasks and specification forms. The framework provides a unified approach for measuring how LLMs resolve conflicts between competing sources of information.
Read the full abstract ▾
All authors Tairan Wang, Liang Zhou, Zikang Zhan, Pingchuan Yan
Artificial Intelligence
HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection
Xiangbo Wang, Jiasheng Zhang, Xingtong Yu et al. (+2 more)
Video misinformation detection is often approached through global
multimodal fusion or free-form
multimodal reasoning. Both paradigms can under-represent localized authenticity cues that arise from coupled interactions among query phrases, contextual text, and short temporal spans of frames. Because such interactions are inherently higher-order, pairwise graph formulations are insufficient to capture multi-way cross-modal dependencies, whereas hypergraphs offer a suitable representation for these relations. We propose HyperClaim, a discriminative temporal hypergraph framework for sample-level authenticity classification. Using the title or
benchmark-provided paired text as a claim-like query, HyperClaim constructs a sparse heterogeneous hypergraph over query
tokens, evidence
tokens, and sampled frames; applies confidence-aware filtering and source budgeting to form compact text-frame and short-range temporal evidence units; performs adaptive soft-incidence
reasoning with residual text-
video calibration; and aggregates textual, visual, and hyperedge states through a discrepancy-aware readout. Without relying on generated rationales or external tool calls, HyperClaim preserves fine-grained cross-modal and temporal structure that global fusion tends to flatten. Under the FactGuard temporal protocol, it achieves 83.7%, 82.0%, and 87.3% accuracy on FakeSV, FakeTT, and FakeVV, respectively, outperforming strong discriminative and
reasoning-centric baselines. Learned incidence and
attention weights further reveal
token- and frame-level structure.
Read the full abstract ▾
All authors Xiangbo Wang, Jiasheng Zhang, Xingtong Yu, Luoqiang Lei, Delvin Ce Zhang
Artificial Intelligence
Zihan Dong, Zhiyuan Ma, Zekun Wang et al. (+5 more)
Computer-use
agents (CUA) are being deployed to browse the web and operate desktop software, yet their
benchmark scores are still commonly produced by brittle scripted oracles. A score is the output of a pipeline in which tasks can be stale, trajectories can omit decisive visual evidence, evaluators can reject valid alternatives, and aggregate reports can hide the cause of failure. We organize these problems into a reliability framework spanning task construction, trajectory observation, scoring, and reporting. We then audit 150 public failure-scored trajectories from five web, enterprise-workflow, and desktop-control
benchmarks, find that 15.3% of FAIL verdicts are wrong: 10.7% are evaluator false negatives and 4.7% are broken tasks. For genuine failures, a three-tier diagnostic taxonomy shows that verification/feedback and planning failures dominate execution/grounding errors, while a single scalar success rate can not explain. We connect these findings to newer long-horizon CUA
benchmarks and derive stage-specific design rules for CUA evaluation.
Read the full abstract ▾
All authors Zihan Dong, Zhiyuan Ma, Zekun Wang, Yunqing Li, Zirou Liu, Ruixuan Deng, Qishi Zhan, Rui Qian
Artificial Intelligence · Cross-listed from cs.CV
ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow
Jin Cao, Zian Meng and Kaipeng Zhang
We present ShadowDancer, a novel approach to any-action, frame-level control of interactive
video world models. The obstacle is representational: existing interfaces either encode an action loosely, leaving how it unfolds for the model to improvise, or encode it exactly through structured signals that serve one family and are hard to acquire, so precise control across diverse dynamics remains impractical. Demonstration
videos are the natural remedy, specifying any dynamics frame by frame; yet a
video shows its dynamics only through one particular appearance, a single shadow of the underlying dynamics, so actions learned from demonstrations transfer poorly to new scenes. ShadowDancer addresses this with two key innovations: (1) shadow pairs,
video pairs that replay the same dynamics under independently resampled appearance, constructed at scale by our Shadow Library, so that a dynamics family becomes controllable exactly when such pairs can be constructed for it; and (2) cross-shadow prediction, which learns actions by predicting one shadow from the other, so that whatever the pairing resamples is discarded by construction and whatever it preserves becomes the action, yielding a unified dynamics representation that drives a block-causal world model. Any demonstrated clip thus becomes a reusable action asset, replayed in new environments without action labels, motion
estimators, or fine-tuning. Experiments demonstrate improved action transfer and long action rollout over strong latent-action and interactive world model baselines across diverse dynamics families, with an average blinded win rate of 86% in rollout comparisons. We show
video results at https://ShadowDancer-1.github.io
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SD
Teffic-Audio: Tell Fact from Fiction
Wan Lin, Li Wang, Jindong Wang et al. (+2 more)
Speech deepfake detection has expanded in scope with increasingly heterogeneous spoofing mechanisms, including
speech synthesis, voice conversion, vocoder reconstruction, and neural-codec resynthesis. The resulting spoofing artifacts can be further shaped by variability in source
speech, recording environments, and transmission channels. This variability makes robust generalization across heterogeneous conditions a central requirement for practical detection systems. This report presents Teffic-Audio, a general
speech deepfake detection system designed for comprehensive evaluation environment. Teffic-Audio adopts a straightforward detector architecture consisting of a Conformer-based
speech encoder, multi-head attentive statistics pooling, and a binary classifier. Rather than relying on additional architectural complexity, the system improves generalization through its training recipe, which integrates multi-source data, attack- and source-balanced sampling, and diverse audio augmentation. Trained only with open-source data, Teffic-Audio achieves a pooled EER of 1.454% on the 14 test sets of
Speech-DF-Arena, outperforming all currently public systems on the leaderboard. It also obtains the lowest EER on five individual test sets and shows a favorable performance-complexity trade-off compared with larger leading systems. Overall, Teffic-Audio provides a strong and practical reference system for general
speech deepfake detection.
Read the full abstract ▾
All authors Wan Lin, Li Wang, Jindong Wang, Kunyu Feng, Zhizheng Wu
Artificial Intelligence
Correcting What You Cannot See: Credit Assignment for Perception Distillation in Multimodal Reasoners
Feng Xiong, Leyan Xue and Hongyu Lin
On-policy
distillation provides dense supervision for
multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent
reasoning. Perception Success Rate (PSR), estimated from multiple reasonings sharing one perception, remains ambiguous because low success conflates perceptual insufficiency with
reasoning difficulty. We introduce Perception-Correction
Distillation (PCD), a label-free method that identifies correctable perception failures using downstream failure and teacher–student disagreement as complementary witnesses. Their product, , forms a soft AND gate that strengthens
distillation only when both witnesses are present. We motivate this rule through
Bayesian evidence combination and show that multiplication is the unique normalized bilinear gate that vanishes when either witness is absent. PCD uses separated perception–
reasoning rollouts and mean-preserving weights, leaving the
reasoning objective unchanged. Across eight
benchmarks, PCD improves the 8B 2B macro average from 44.50 with OPD to 47.28 and the 32B 8B result from 56.94 to 61.22. In matched 2B ablations, removing PCD and separated rollout reduces held-out average by 2.22 and 0.88 points, respectively. Effective
multimodal distillation therefore depends not only on what the teacher predicts, but also on identifying when perception is the appropriate target of correction.
Read the full abstract ▾
Artificial Intelligence
Paying for Honesty Without Knowing the Truth: Reputation-Penalty Design for LLM Marketplace Agents
Mingdai Yang, Shicheng Fan, Kejing Yu et al. (+5 more)
LLM
agents increasingly act as autonomous merchants that write their own product listings, and under competitive pressure, they fabricate attributes to win sales. Even under instructions to be honest, they fabricate attributes in a majority of listings across models. A platform's obvious remedy—verifying each claim against the truth—is unavailable, because it observes only a noisy, biased complaint signal, never the ground truth. We design CARP, a reputation-penalty mechanism with a deadband that forgives complaint noise and a state-dependent severity that counters reputation-driven detection erosion. CARP requires no product-level ground truth and is robust to strategic gaming. CARP protects consumers by suppressing the sales volume of low-rated liars while sparing honest sellers. Paired with SPARC, it closes most of the consumer-welfare gap relative to a perfect-information oracle, without ever accessing the truth. It also achieves the best welfare of the policies we compare. We further show that this felt penalty becomes behaviorally binding through SPARC, a byte-clean code-gated reflection mechanism: LLM merchants fabricate when lying is free but restrain themselves when fabrication costs them sales, a self-interested response rather than compliance. We trace this distinction to penalty-gated self-correction
reasoning, and observe the binding across models, with supporting confidence intervals.
Read the full abstract ▾
All authors Mingdai Yang, Shicheng Fan, Kejing Yu, Duohao Wang, Li Sun, Hao Peng, Philip S. Yu, Zhiwei Liu
Artificial Intelligence
PathView-Bench: Can Multimodal Large Language Models Achieve Fine-grained Multiscale Understanding of Pathology Images?
Zongyi Chen, Yu Liang, Jie Lin et al. (+1 more)
Multimodal large
language models (MLLMs) are increasingly used to analyze pathology images. However, dominant
multimodal benchmarks in pathology mainly score final diagnostic answers, captions, or reports. These evaluations provide limited insight into whether a model understands the multiscale visual content needed for pathology
reasoning and decision-making. We introduce PathVU, a
vision-anchored
benchmark for fine-grained and multiscale visual understanding in computational pathology. Built from 23 public pathology imaging
datasets with human-supervised labels and spatial annotations, PathVU evaluates MLLM understanding in two fields of view: Region FOV for high-resolution local regions and Slide FOV for macro whole-slide views. By converting raw annotations into deterministic task targets, PathVU enables programmatic scoring of region localization, visual recognition, quantity estimation, spatial
reasoning, and insufficient-context judgment. The
benchmark contains 14 VQA-style tasks, 61,673 images, and 308,070 samples across 28 organs and 7,253,526 annotations. Evaluating 18 representative general-purpose, medical-domain, and pathology-oriented MLLMs, we observe substantial limitations even in advanced models on fine-grained visual tasks across multiscale pathology images. PathVU provides a reproducible basis for developing and evaluating pathology MLLMs with explicit multiscale visual understanding.
Read the full abstract ▾
All authors Zongyi Chen, Yu Liang, Jie Lin, Liansheng Wang
Artificial Intelligence
One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
Cesare Zavattari, Alessandro Tommasi and Giuseppe Prencipe
A single human must audit $N$ LLM
agents under a budget of $B \ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $\delta^*$ past which confidence-ranked
auditing is worse than random. Two a-priori expectations reverse: $\delta^*$ rises as the budget shrinks, and cross-family correlation is not low—shared difficulty dominates lineage. Five open-weight LLMs show operationally useless (near-constant) confidence, point estimates at or beyond the flip though CIs straddle it; a proprietary model is informative and lands below it. We give a quantitative criterion for vacuous oversight, and replaying policies on recorded traces confirms the ordering.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding
Mingkang Dong, Muxin Pu, Jie Li et al. (+8 more)
Streaming
video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to
token importance, temporal redundancy, or segment-level relevance, but rarely organize evidence around objects that persist and evolve over time. Thus, in this paper, we introduce ObjectStream, a training-free framework that treats latent objects as
memory anchors for streaming
video understanding. ObjectStream induces spatially coherent latent objects directly from frozen
Video-LLM representations, links them across frames into persistent anchors, and maintains their histories under a bounded
memory budget, without requiring external object detectors or
segmentation models. Built on these anchors, ObjectStream preserves three complementary forms of evidence: persistent object histories, transient object changes, and recent visual context. This design enables existing
Video Large
Language Models (
Video-LLMs) to reason over object identities, interactions, and state changes while leaving the underlying model unchanged. Extensive experiments on online streaming and offline long-
video benchmarks demonstrate both effectiveness and efficiency. In online streaming evaluation, ObjectStream improves Qwen2.5-VL-7B by 10.0 points on OVO-Bench Real-Time Visual Perception, while reducing peak GPU mem-ory and TTFT by approximately 50%. On offline long-
video benchmarks, it surpasses the full-
token baseline while discarding 82.5% of visual
tokens. These results highlight latent objects as a practical and effective organizing principle for compact streaming
video memory.
Read the full abstract ▾
All authors Mingkang Dong, Muxin Pu, Jie Li, Bohan Guo, Songruo Chen, Bin Ren, Xu Zheng, Chen Zhao, Tianwen Qian, Mohamed Elhoseiny, Yuqian Fu
Artificial Intelligence · Cross-listed from cs.SE
From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis
Danyllo Albuquerque, José Renan, Guillermo Rodríguez et al. (+6 more)
Microservice architectures have become dominant for modernizing monolithic systems, yet identifying appropriate services remains challenging and largely manual. Existing decomposition approaches are predominantly code-centric, limiting applicability in early design stages where only textual requirements are available. Despite advances in Large
Language Models (LLMs), limited empirical evidence exists on their ability to synthesize complete microservice architectures from natural-
language requirements, including service definitions and inter-service interactions. This study investigates whether an LLM can bridge requirements engineering and architectural design, generating architectures solely from textual requirements and evaluating structural agreement and perceived quality of results. We conduct a mixed-method study using OpenAI o3 under zero-shot (ZS) and few-shot (FS) prompting across two systems (Bookstore, PetClinic), one execution per system/condition. Architectures are evaluated through (i) comparison with reference architectures using precision, recall, and F1-score for service identification and communication recovery, and (ii) a blinded expert assessment of correctness, completeness, modularity, and plausibility, plus open feedback synthesis. OpenAI o3 identifies services with higher agreement under FS prompting (F1 = 0.79 for ZS versus = 0.97 for FS). Communication recovery is more challenging: ZS produces dense architectures with high recall but low precision (F1 = 0.61), while FS improves agreement, reaching F1 = 0.82 and reducing unsupported dependencies. Expert evaluation corroborates these results, with FS architectures perceived as more modular, coherent, and plausible than ZS outputs. OpenAI o3 shows potential for requirements-driven synthesis when guided by exemplar prompting. Results are model- and context-specific from two small systems, not model-independent proof.
Read the full abstract ▾
All authors Danyllo Albuquerque, José Renan, Guillermo Rodríguez, Guillermo Rodríguez, Emanuel Dantas, Ademar França, Mirko Perkusich, Kyller Gorgônio, Angelo Perkusich
Artificial Intelligence · Cross-listed from cs.CV
MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians
Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi et al. (+1 more)
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural
language. However, current 3D Gaussian frameworks are often bottlenecked by restrictive multiview capture requirements, costly scene-specific optimization, and the massive
memory overhead of storing dense
language features. We present a novel, training-free pipeline that fundamentally reimagines this paradigm by explicitly decoupling 3D
geometric reconstruction from semantic integration. Given a standard
monocular video sequence as input, our method efficiently outputs a compact, highly interpretable, and fully searchable object-level semantic Gaussian map. Rather than entangling heavy
language embeddings within the mapping loop, we extract geometry independently and ground semantics through a lightweight, modular post-processing framework. Extensive evaluations on the Replica
dataset demonstrate that this decoupled architecture preserves strong rendering fidelity and competitive
segmentation accuracy. Crucially, by replacing dense per-Gaussian storage with modular, object-level semantic
embeddings, our approach delivers an order-of-magnitude reduction in
memory usage compared to SOTA baselines. This provides a highly efficient, scalable, and practical solution for open-vocabulary 3D
retrieval and question answering directly from everyday
monocular video.
Read the full abstract ▾
All authors Pouya Ardekhani, Zahra Dehghanian, Morteza Abolghasemi, Hamid R. Rabiee
Artificial Intelligence · Cross-listed from cs.CL
CACHE-UK: A Stability-Aware Memory Editor for Sequentially Updated Quantized LLMs in Finance
Anubhav Lakra and Yue Feng
Large
Language Models (LLMs) deployed in dynamic financial environments face a critical challenge: maintaining factual accuracy as
market conditions, regulations, and corporate facts change continuously. While 4-bit quantization enables efficient deployment, it severely limits the viability of sequential
memory editing: existing methods undergo catastrophic performance degradation under this "quantization stability crisis." We introduce CACHE-UK (Contextual Adaptive Continual Hybrid Editor for UK Finance), a stability-aware
memory editing framework specifically designed for domain-specific, quantized LLMs. CACHE-UK integrates three components: a rank-1 LoRA perturbation mechanism that confines edits to the low-rank adapter subspace, a financial domain prioritization module for content-adaptive edit strength, and a closed-loop Stability Controller that tracks "degradation debt" to prevent catastrophic forgetting across sequential updates. Evaluated on a 4-bit quantized OpenLLaMA-3B model with a curated UK financial corpus of 88,021 documents, CACHE-UK reduces knowledge degradation by 11-17% relative to adapted baselines under identical 4-bit constraints – its most robust effect – while attaining the highest test success (generalization) rate observed in our setting (28%, a 6 percentage point improvement over the strongest adapted baseline). These results indicate that stability-aware editing can improve factual maintenance in resource-constrained financial LLM deployments, though absolute generalization rates remain low.
Read the full abstract ▾
Artificial Intelligence
Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3
Jens Lehmann, Andrei Aioanei and Sahar Vahdati
ARC-AGI-3 turns abstraction into an interactive problem of skill acquisition. A player must infer an unfamiliar game's rules, hidden state, and goal while maintaining action efficiency because every move counts. We formalize these environments as parameterized rendered deterministic Moore machines and introduce Tycho, a coding-
agent system that constructs and uses game-specific models during interaction. Tycho separates actionable observations from intermediate animation, level-completion, and game-over frames. From this structured history, an
agent can model, test, plan with, repair, or bypass a free-form executable hypothesis. In one matched public-set run per policy, we compare four orchestration policies on all 25 public games using Claude Opus 4.8 under matched inference budgets. Actor-requested delegation to a model builder obtains the highest observed mean Relative Human Action Efficiency (RHAE), 88.49. With this selected policy, GPT-5.6 Sol and Opus 5 both reach 100.00 RHAE and complete all 183 levels. Their game-balanced first-run human-replay midranks are 98.5 and 100.0. Opus 5 uses 61% fewer scored actions than the aggregate official human baselines. Automatic repair after verification failures produces models that reproduce observed transitions much more accurately, yet reaches only 83.07 RHAE. Transition match indicates whether a simulator reproduces observed dynamics, not whether it has identified the objective or improves the next action. Strong play also requires deciding when to construct, repair, use, or bypass a model. We call this joint problem active abstraction: generating a testable model from costly interaction and deciding when acquiring or using it is worth its cost.
Read the full abstract ▾
Artificial Intelligence
MemHarness: Memory Is Reconstructed, Not Replayed
Rong Wu, Daocheng Fu, Licheng Wen et al. (+10 more)
Retrieving past experiences has become a common strategy to enhance large
language model
agents. However, most existing
memory-augmented
agents treat retrieved experiences as static records to be replayed verbatim, injecting them into the context regardless of whether they align with the
agent's current situation. This “replay” paradigm ignores the gap between the abstract, general nature of stored experience and the concrete, ever-changing states encountered at decision time, frequently causing negative transfer. In contrast, humans rarely recall past experiences verbatim; instead, they reorganize and adapt retrieved
memories to fit the present context. Inspired by this, we propose MemHarness, a framework that equips LLM
agents to actively harness and reconstruct past experiences based on the present context. At each decision step, a unified policy model critiques and reconstructs the retrieved experience conditioned on the current state, producing context-grounded guidance before acting. This reconstructive ability emerges naturally through end-to-end training with GRPO. Experiments on ALFWorld and WebShop show that MemHarness substantially outperforms pure RL and static
memory-augmented baselines, demonstrating strong robustness in out-of-distribution (OOD) scenarios. Furthermore, our analyses reveal that this reconstruction objective not only prevents negative transfer but also serves as latent guidance during training, fundamentally improving the
agent's intrinsic
reasoning capabilities.
Read the full abstract ▾
All authors Rong Wu, Daocheng Fu, Licheng Wen, Xuemeng Yang, Shu Zou, Jianbiao Mei, Yuxin Wang, Hairong Zhang, Yu Yang, Tao Hu, Cong Zhang, Botian Shi, Pinlong Cai
Artificial Intelligence · Cross-listed from cs.SE
Agentic Method for Deterministic Validation of Legacy Code Migration
Andras Ferenczi, Jordan Docherty, Mariya Bessonov et al. (+2 more)
Migration of legacy COBOL programs to Java requires extensive testing to ensure correct functionality. This effort is often complicated by the lack of test data and the difficulty of validating all corner cases. In this paper we propose a novel agentic test-synthesis method, the "Locksmith Loop," which is initiated by preparing two runtime environments: the COBOL source and the generated Java target are each instrumented with mocks and executed off-mainframe on commodity hardware, then an iterative agentic loop performs Witness Search over input mocks to penetrate program branches, followed by parity-preserving mutations. When routing boundaries are reached, an analyzer identifies a Locked Paragraph: a condition preventing deeper exploration. Across three COBOL-Java case studies, spanning two open-source programs and one internal production-like COBOL program and ranging from 430 to 4,114 source lines, Locksmith consistently improved coverage beyond input-search plateaus, reaching nearly complete coverage on the two open-source programs and 91.90% branch coverage on the internal production-like COBOL program. The generated Java matched the COBOL reference under deterministic parity checks in all accepted test cases. Through these findings we demonstrate, to the best of our knowledge, a novel approach for validating agentic coding output using a deterministic oracle.
Read the full abstract ▾
All authors Andras Ferenczi, Jordan Docherty, Mariya Bessonov, Matthew Findlay, Krishna Lingamneni
Artificial Intelligence · Cross-listed from cs.CV
Theia: Large-Scale Multimodal Captioning and Automated Validation of the Incidents1M Dataset for Data-Free Distillation
Simone Giano, Lorenzo Severini, Alessandro Galdelli et al. (+1 more)
The deployment of
Vision-
Language Models (VLMs) in critical domains like disaster management requires high-quality
multimodal datasets, especially for transferring knowledge via Data-Free Knowledge
Distillation (DFKD). However, existing
datasets in this domain either entirely lack descriptive text, such as Incidents1M, or suffer from severe text-image semantic misalignment, such as CrisisMMD. In this work, we present a novel methodology to construct and automatically validate a large-scale
multimodal dataset for disaster response. Starting from the
vision-only Incidents1M, we successfully recovered 100,000 images and generated high-fidelity textual descriptions using two distinct Qwen3.5 architectures: a 4B dense model and a 35B Mixture-of-Experts (MoE) model. To ensure the generated captions provide reliable semantic anchoring for DFKD, we introduce an image-blind LLM-as-a-Judge validation pipeline leveraging Qwen3.5-9B. By intentionally obscuring the original image from the judge, this evaluator accurately simulates the modality gap of the student model during data-free
distillation. Our evaluation across 173,179 label pairs demonstrates a high semantic agreement (78.65/100) between the two architectures. Furthermore, the automated evaluation reveals a conservative captioning behaviour, characterized by a high Precision (77.6%) and low Recall (46.0%). This minimizes the false positive noise, while simultaneously exposing underlying human annotation inconsistencies in the original ground truth. This work provides a scalable, LLM-validated
multimodal dataset and a reproducible framework to advance cross-modal knowledge
distillation.
Read the full abstract ▾
All authors Simone Giano, Lorenzo Severini, Alessandro Galdelli, Adriano Mancini
Artificial Intelligence
LLM-Guided Evolutionary Search for Constraint Model Reformulation to Improve Solver Efficiency
Kostis Michailidis, Dimos Tsouros, Nguyen Dang et al. (+1 more)
Combinatorial problems appear in numerous industrial applications. A common approach is to formulate these problems as declarative constraint models that can subsequently be compiled to and solved by a range of back-end solvers. Recent work shows that Large
Language Models (LLMs) can produce correct models from natural
language, but even a correct model can be expensive to solve because performance remains sensitive to modelling choices. In this work, we investigate whether LLMs can automate performance-oriented model reformulation. Inspired by Automatic Heuristic Design (AHD), we use an evolutionary framework in which an LLM proposes candidate reformulations that are verified and benchmarked against the user-defined baseline model. We compare AHD-adapted search strategies that control which prior attempts, instructions, and measured feedback enter each
prompt. Existing retention strategies prioritize recency or performance, but do not explicitly diversify the context. To cover this gap, we introduce Profile-Diverse Retention (PDR), which applies Maximal Marginal Relevance (MMR) to instance-level runtime vectors to retain behaviourally diverse attempts. We systematically evaluate the strategies on eight CSPLib problems using validation-based final model selection. The results show that: (i) iterative reformulation can produce substantial held-out speedups; (ii) strategies that keep the retained context diverse outperform those that retain only recent or the fastest attempts; and (iii) validation-based selection improves the held-out speedup of every strategy.
Read the full abstract ▾
All authors Kostis Michailidis, Dimos Tsouros, Nguyen Dang, Tias Guns
Artificial Intelligence
Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing
Dheeraj Poolavaram, Aanchal Rajesh Chugh and Sebastian Dorn
The online three-dimensional bin packing problem (3D-BPP) is a longstanding challenge in logistics and industrial palletizing. Recent learning-based methods use a learned policy to select among feasible candidate placements. Performance depends on the candidate generator and representation, especially in industrial settings where packings must be space-efficient, stable, compact, and balanced. However, prior work has mainly optimized the policy, while candidate generation and representation remain largely geometry-driven. We address this gap with OPAL, an operationally guided placement-aware learning framework for industrial online 3D-BPP which combines an Operationally Guided Empty-Maximal-Space generator (OG-EMS), an operational representation for each candidate placement, and a masked ranking policy trained with proximal policy optimization. OG-EMS evaluates multiple anchors within each free-space region and prioritizes low, well-supported, compact, and spatially diverse placements. An xLSTM-based Placement Encoder models dependencies among
geometric and operational candidate attributes, while a lightweight recurrent core combines the resulting
embeddings with the current item and pallet state to rank feasible actions. On the BED-BPP
benchmark, OPAL achieves a mean space utilization of 0.49, with improvements of 15.1% from operationally guided candidate generation and 6.3% from learned ranking, while maintaining robust inference-time performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
Zexuan Yan, Yuzhou Wu, Yue Ma et al. (+9 more)
Egocentric video offers rich manipulation experience for
embodied AI, yet collecting diverse
egocentric data across scenes, objects, motions, and embodiments remains costly. We present \method, an
egocentric world-action simulator that synthesizes controllable, high-quality manipulation
videos to expand scarce real-world training data. \method{} builds on a pretrained
video generation prior and introduces two geometry-aware conditioning mechanisms. Online Anchored Projective
Memory (OAPM) preserves a first-frame 3D scene anchor while periodically refreshing a recent state during autoregressive generation. Action-3D Rotary Position
Embedding (A3D-RoPE) encodes end-effector motion with camera-aware 3D rotary coordinates, injecting action geometry into skeleton-to-
video cross-
attention for precise control. Together, these components improve visual fidelity,
geometric stability, and action
alignment in long
egocentric rollouts. Moreover, augmenting 400 real trajectories with 400 \method-generated trajectories improves out-of-distribution real-
robot success from 77% to 84% on single-arm tasks and from 53% to 70% on dual-arm tasks, demonstrating that the synthesized data substantially improve downstream WAM generalization.
Read the full abstract ▾
All authors Zexuan Yan, Yuzhou Wu, Yue Ma, Zonghang He, Kaibo Yin, Xiaobing Tu, Yinggui Wang, Jinkui Ren, Xiantao Zhang, Shijian Wang, Jinghong Liu, Linfeng Zhang
Artificial Intelligence · Cross-listed from cs.SE
Agentic Metaverse Services: A New As-a-Service Paradigm
Xiaofei Xu, Quan Z. Sheng, Zhongjie Wang et al. (+3 more)
Generative Artificial Intelligence (GenAI) is reconstructing the digital virtual world, upgrading
agents through enhancing their abilities in autonomous learning, multi-modal interaction, content generation, and collaborative decision-making. In particular, the shift from conversational chatbots to agentic AI, the most recent significant technical breakthrough of GenAI, has brought a new form of services, agentic services and
Agent-as-a-Service (AaaS), in which the
agent's abilities are encapsulated, such as perception, decision-making, execution, collaboration, and content generation, to provide the customized
agent services to users. The metaverse is a virtual ecosystem for human life, work, creation, and entertainment, supported by the new generation of digital technologies. Through combining agentic services and the metaverse, an Agentic Metaverse Service, denoted as AMServ, is produced for metaverse business processing, as a new form of metaverse service. The AaaS in the metaverse environment, denoted as Meta-AaaS, as an approach to realize AMServ, has become a new paradigm of agentic services and service computing. This paper overviews the
evolution and new features of
agents and services empowered by GenAI, reveals the roles and principles of agentic services in the metaverse environment, presents the forms, characteristics, and principles of the AMServ and the Meta-AaaS, discusses the typical application examples of the AMServ and the Meta-AaaS, and finally points out the new tendencies and research directions of the AMServ and the Meta-AaaS. The AMServ and the Meta-AaaS will bring great opportunities to human society and services in the AI era, and promote the rapid development of emerging service industries in the future.
Read the full abstract ▾
All authors Xiaofei Xu, Quan Z. Sheng, Zhongjie Wang, Boualem Benatallah, Xiao Wang, Ruipeng Han
Artificial Intelligence
AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge
Muhammad Sajjad Akbar
Generative Artificial Intelligence (AI) is increasingly used by Muslims for religious guidance, Qur'anic interpretation, Hadith explanation, jurisprudential rulings, and Islamic education. Despite its growing adoption, there is limited empirical evidence on whether current AI systems provide authentic, verifiable, and trustworthy Islamic knowledge suitable for high-trust religious contexts. This study evaluates six leading generative AI systems using fifty realistic open-ended Islamic questions covering Qur'anic interpretation, Hadith, Fiqh, ethics, pastoral advice, and Madhhab-sensitive topics. Responses were collected under real-world conditions from participants in Australia and the United Kingdom and analysed using a mixed-method framework examining domain accuracy, citation verification,
hallucinations, jurisprudential consistency, uncertainty handling, source provenance, and geographical variation. The study addresses four research questions: (1) How accurate and authentic are AI-generated responses across major Islamic knowledge domains? (2) To what extent do AI systems produce
hallucinations, incomplete citations, or unverifiable religious references? (3) How consistently do models handle jurisprudential disagreement, Madhhab diversity, and uncertainty? (4) Are current AI systems sufficiently reliable for religious guidance, Islamic education, and scholarly research? Overall, current generative AI systems are valuable as assistive tools for introductory Islamic learning but should not be treated as authoritative sources for religious rulings or Islamic research without verification against authenticated primary sources and qualified scholarly expertise. This study provides one of the first comprehensive empirical evaluations of AI reliability within Islamic knowledge, offering practical guidance for researchers, educators, AI developers, and the wider Muslim community.
Read the full abstract ▾
Artificial Intelligence
CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising
Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand et al. (+1 more)
Pre-trained
language models have significantly improved sentence representation learning, yet their
embeddings remain sensitive to textual perturbations such as synonym substitution, masking, and word dropout. This work proposes a lightweight Contrastive Denoising Autoencoder (CDAE) that refines pre-trained BERT
embeddings by jointly optimizing contrastive and reconstruction objectives to learn perturbation-invariant representations. We evaluate the proposed framework under multiple perturbation strategies and strengths, and compare it against the original BERT
embeddings and SimCSE. Experimental results show that CDAE consistently preserves higher
embedding similarity under perturbation, with the gap widening as the perturbation strength increases, highlighting perturbation-invariant learning as a promising direction for improving the stability of sentence
embeddings. The source code is publicly available at: https://github.com/ComputationIASBS/CDAE
Read the full abstract ▾
All authors Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand, Majid Ramezani
Artificial Intelligence · Cross-listed from cs.CL
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
Luigi Sigillo, Matteo Silvestri, Francesco Tabaro et al. (+9 more)
The web is increasingly accessed by AI
agents rather than humans. Every
agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI
agents: they take keywords and complex syntax and return whole papers, so every
agent must learn the syntax, issue several searches, and read full papers to find the evidence it needs. We introduce EMBL AI Librarian, a knowledge layer that upgrades the Europe PMC interface for AI
agents: an
agent asks in natural
language and receives evidence that answers it. A single LLM orchestrates the whole knowledge
retrieval process: it plans complementary subqueries executed by the live Europe PMC search engine, then reads the selected papers and locates the relevant evidence. We evaluate Librarian across four
benchmarks: literature synthesis, claim verification, open-domain question answering, and downstream biology tasks such as protocol questions and sequence manipulation. On ScholarQABench, Librarian improves Citation F1 by more than $16$ points over strong recently published baselines. Used as the
retrieval layer of an existing claim-verification pipeline, it increases agreement with expert consensus; and on the open-form LitQA2
benchmark, a GPT-5.4
agent scores about $8$ points higher when grounded in Librarian than with web search. Overall, our results show that equipping life-science
agents with the Librarian knowledge layer improves performance across a range of tasks. We release our code publicly at https://github.com/petroni-lab/librarian
Read the full abstract ▾
All authors Luigi Sigillo, Matteo Silvestri, Francesco Tabaro, Rajat Bhatnagar, Syed Irtaza Mubashar, Matt Jeffryes, Daljit Nijjer, Vittorio Perera, Ola Spjuth, Julio Saez-Rodriguez, Melissa Harrison, Fabio Petroni
Artificial Intelligence
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
Hanzhang Zhou, Panrong Tong, Xu Zhang et al. (+13 more)
GUI
agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision
agents that operate reliably on real devices, execute workflows across platforms, combine GUI interaction with CLI execution, complete long-horizon tasks, proactively initiate useful services, and autonomously improve their capabilities with minimal human effort. Guided by this
vision, we present Qwen-UI-
Agent, a real-world centric foundation GUI
agent spanning mobile, computer-use, web, and DeepSearch environments. Qwen-UI-
Agent combines diverse sandbox environments with a large-scale real-device mobile runtime. Its unified action space interleaves GUI operations with CLI execution and generates batched actions in a single model turn. An AutoResearch-style data flywheel uses
agents to construct tasks and environments, diagnose failures, and plan subsequent iterations. Online RL supports training on trajectories exceeding 100 turns, with over 10,000 concurrent environments accelerating rollout. A lightweight harness layer supports proactive service initiation and stateful workflows across mobile and computer. Across a broad suite of evaluations, Qwen-UI-
Agent sets state-of-the-art performance on mobile-use
benchmarks while delivering competitive performance on computer- and browser-use tasks against frontier models, including Opus 4.8, Gemini 3.1 Pro, and GPT-5.6 Sol. On mobile use, it achieves 82.1% on MobileWorld, 92.2% on MobileWorld-Real, and 97.5% on AndroidDaily. On computer use, it achieves 79.5% on OSWorld-Verified and a 40.0% partial-progress score on OSWorld-v2. On browser use and GUI grounding, it achieves 73.6% on WebArena and 81.5% on ScreenSpot-Pro, respectively.
Read the full abstract ▾
All authors Hanzhang Zhou, Panrong Tong, Xu Zhang, Quyu Kong, Chenglin Cai, Tianyu Xia, Gongjie Zhang, Jianan Zhang, Long Li, Long Chen, Lei Wang, Gaole Dai, Pengxiang Li, Liangyu Chen, Yue Wang, Steven Hoi
Artificial Intelligence · Cross-listed from cs.CR
Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation
Fazhong Liu, Zhuoyan Chen, Haozhen Tan et al. (+3 more)
World models give
embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors,
prompts, or feedback into physical action. Rather than treating world models as an isolated component, this survey traces threats across their entire lifecycle-from data construction and representation learning, through state grounding and imagination, to trajectory evaluation, execution, and long-term adaptation via
memory and tools. We show that familiar attack families: poisoning,
backdoors,
adversarial examples, sensor spoofing,
prompt injection, trajectory manipulation, and supply-chain attacks take on distinct meanings when they corrupt world states, learned dynamics, affordance estimates, or safety costs. We also highlight a duality: world models can serve as runtime safety shields, yet when compromised or over-trusted they generate predictive safety illusions. The survey offers a lifecycle taxonomy, maps existing attacks to world-model security properties, outlines evaluation protocols for safety failures, and structures defenses across provenance, robust grounding, uncertainty-aware prediction, trajectory gating, feedback
auditing, and deployment assurance.
Read the full abstract ▾
All authors Fazhong Liu, Zhuoyan Chen, Haozhen Tan, Yan Meng, Guoxing Chen, Haojin Zhu
Artificial Intelligence · Cross-listed from physics.app-ph
Vibe-FDTR: An agent-oriented framework for reproducible frequency-domain thermoreflectance data analysis
Fuwei Yang, Weiheng Li and Bai Song
Frequency-domain thermoreflectance (FDTR) is a
laser pump-probe technique widely used to measure thermal properties at the micro- and nanoscale; however, it relies on a complex data analysis procedure that demands substantial domain expertise and is susceptible to subtle human errors. Here, we present Vibe-FDTR, an
agent-oriented framework that enables large
language model (LLM)
agents to perform reliable and reproducible FDTR analyses directly from natural
language requests. This framework couples a configuration-driven FDTR code package, which enforces physical and parametric consistency, with procedural
agent skills that translate user intentions into organized and verifiable analysis steps. We evaluate Vibe-FDTR using a controlled
benchmark with two levels: synthetic single-step tasks and real-data multi-step tasks based on measurements of gold-coated graphite samples. Across the two levels,
agents using Vibe-FDTR achieve success rates of 100% and 98.9%, respectively. In sharp contrast, ablating skills (Code-
agent) reduces performance to 91.4% and 36.7%, which drops further to 38.6% and 0% when the domain package is also omitted (
Agent-only). Beyond success rate, Vibe-FDTR also reduces computational cost by 87.7% relative to the Code-
agent variant and cuts execution time by more than 60%. Finally, an optional expert mode supports experimental planning via autonomous sensitivity and uncertainty evaluations, and formulates physically grounded recommendations for underspecified tasks. These results demonstrate that encapsulating domain code and expert knowledge into
agent skills offers a promising route toward low-barrier, autonomous, and trustworthy thermal metrology.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
The MADRS Pipeline: Supporting Depression Assessment in Clinical Trials
Mila Fodor, Katalin Ócsai, Francesco Periti et al. (+2 more)
Depression is a major mental disorder for which diagnosis relies primarily on clinical assessments. Automated methods to support its detection via the psychiatric MADRS scale are getting more and more
attention. While existing solutions primarily focus on detecting the disorder from different text sources (e.g., online text, social media), there is still limited support for clinical trials, where clinical assessments are conducted through structured interviews based on standard guidelines such as SIGMA. In this work, we develop a LLM pipeline specifically designed to support clinicians in supporting the assessment of depression in patients enrolled in clinical trials. Our pipeline converts audio interviews into transcripts, maps them into the ten MADRS symptom items, estimates their severity, and identify problematic clinical ratings associated with them. Evaluation on real clinical interviews shows a strong overall correlation of 0.867 with expert ratings, providing interpretable support for future assessments in clinical trials.
Read the full abstract ▾
All authors Mila Fodor, Katalin Ócsai, Francesco Periti, Rien Sonck, Alex Boudreau
Artificial Intelligence
Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji et al. (+2 more)
While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- erage and contextual understanding. Recently, commercial
multimodal moderation APIs built on large foundation models have been introduced with the promise of providing broader and more capable safety filters. In this work, we analyze whether this shift also yields more robust image moderation. We conduct a large-scale black-box evaluation on three established commercial image-moderation services and compare their robustness. By evaluating seven simple, model-agnostic image transformations across multiple providers,
datasets, harm categories, perceptual-similarity constraints, and transformation intensities, we find that: (1) all three commercial services can be bypassed using inexpensive image transformations that require no gradients, surrogate models, or knowledge of the target system; (2) even fixed transformations such as color inversion and grayscale conversion induce unsafe-to-safe decision changes while preserving content that remains recognizable to humans; (3) their robustness varies substantially across
datasets and harm categories, with
multimodal content and self-harm exhibiting pronounced vulnerabilities. This yields the conclusion that replacing conventional moderation classifiers with foundation-model-based APIs does not, by itself, provide a reliable security boundary. Such systems must be evaluated under realistic transformations and deployed as one component of a layered moderation pipeline rather than as standalone safety filters.
Read the full abstract ▾
All authors Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji, Tegawendé F. Bissyandé, Jacques Klein
Artificial Intelligence · Cross-listed from cs.LG
Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
Mostafa Haghir Chehreghani
Oversmoothing is a fundamental limitation of deep graph neural networks (GNNs), where repeated message passing causes node representations to become increasingly similar, eventually collapsing toward a low-dimensional subspace. This phenomenon limits the effective depth of message-passing architectures and motivates the search for mechanisms that preserve representation diversity. In this paper, we study a recurrent graph neural network in which independent Gaussian noise is injected after every propagation step and analyze the resulting architecture as a
stochastic dynamical system. Under a standard global contraction assumption on the deterministic update, we prove that the hidden representations form a geometrically ergodic Markov chain admitting a unique invariant probability measure. Our main theoretical result establishes an explicit positive lower bound on the expected stationary Dirichlet energy, proportional to both the noise variance and the spectral gap of the underlying graph. Consequently, the stationary representations cannot collapse onto the constant
manifold, providing a rigorous guarantee that asymptotic oversmoothing is prevented in the sense of non-vanishing Dirichlet energy. Our analysis reveals persistent
stochastic perturbations as a fundamentally different mechanism for combating oversmoothing, complementing existing deterministic approaches based on residual connections, normalization, and graph rewiring. Finally, numerical experiments on both linear and nonlinear recurrent graph neural networks closely match the theoretical predictions, illustrating the emergence of a stationary distribution and the predicted dependence of the limiting Dirichlet energy on the noise intensity.
Read the full abstract ▾