Artificial Intelligence
Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration
Yilin Zhang, Han Jiang, Cai Xu et al. (+2 more)
Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing model pools and deployment budgets. We propose Calibration-Aware Uncertainty Cascades (CAUC), a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data. The resulting calibrated confidence scores establish a common reliability scale for accepting an early prediction, invoking a stronger model, or selectively combining model outputs. This unified decision criterion decouples deployment policies from any particular model pool or operating budget. We further show theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee. Extensive experiments demonstrate that, across six
language benchmarks, CAUC achieves an average relative accuracy improvement of 1.9% over strong-model-only inference while avoiding approximately 47% of strong-model calls. On image classification
benchmarks, it maintains or improves predictive performance while reducing measured GFLOPs by up to 57%.
Read the full abstract ▾
All authors Yilin Zhang, Han Jiang, Cai Xu, Ying Liu, Wei Zhao
Artificial Intelligence
LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study
Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz et al. (+6 more)
Genetic Programming and its variants, such as grammatical
evolution, are widely used in Symbolic Regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be complex or scientifically inconsistent. In this study, we explore whether Large
Language Models, can assist in improving the explainability of Symbolic Regression models generated by evolutionary computation methods. Building upon our previous work on estimating body fat percentage using grammar-based Genetic Programming , we investigate the use of LLMs as post-processing tools to analyze and rank evolved expressions according to their interpretability and medical plausibility. Four symbolic expressions are analysed by three LLMs over three repeated runs, and the resulting interpretations and rankings are assessed by a panel of three clinicians. Across the three LLMs, comparative model-ranking outputs received more favorable clinician assessments than isolated term-level interpretations. However, the LLMs also produced physiologically and mathematically questionable explanations, indicating that they are better suited to comparative
auditing under expert oversight than to autonomous validation.\blfootnote{The present work is an extended version of a paper submitted into a journal.
Read the full abstract ▾
All authors Jorge López-Varela, J. Ignacio Hidalgo, José-Manuel Muñoz, Omar Costilla-Reyes, Esther Maqueda, Jesus Moreno-Fernandez, Tomás González-Vidal, J. Manuel Velasco, Oscar Garnica
Artificial Intelligence · Cross-listed from cs.CL
SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations
Yu Wang, Yuchen Li, Rui Kong et al. (+11 more)
Large
language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing routers are effective in single-turn settings, they do not directly transfer to multi-turn dialogue, where routing performance critically depends on how historical context is segmented, retained, and incorporated into the current
prompt. This introduces two fundamental challenges: preventing information loss and information confusion during context construction, and evaluating routing quality without conflating model selection with
prompt construction quality. In this paper, we propose SWRouter, a Similarity-Contractive Window Router for multi-turn large
language model routing. SWRouter combines a similarity-based context
segmentation mechanism for
prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance. Experiments on multi-turn dialogue
benchmarks demonstrate that SWRouter consistently surpasses strong baselines, achieving a 16.26% improvement in evaluation accuracy over the best individual large
language model and an additional 8.22% gain over the Conv-ID Context baseline. Our results highlight that multi-turn large
language model routing requires a joint design of context construction and evaluation, rather than a direct extension of single-turn routing methods.
Read the full abstract ▾
All authors Yu Wang, Yuchen Li, Rui Kong, Xinran Chen, Jiamin Chen, Hengyi Cai, Shuaiqiang Wang, Jiashu Zhao, Yulun Zhang, Zhonghao Lyu, Haoyi Xiong, Linghe Kong, Jimmy Xiangji Huang, Dawei Yin
Artificial Intelligence · Cross-listed from cs.SD
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Haojun Zhang, Yi Zou, Min Chen et al. (+7 more)
Reducing audio-encoder depth lowers the inference cost of
speech large
language models, but removing complete blocks perturbs the
embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation
alignment, cross-scale
distillation, scheduled student-policy supervision, and LoRA finetuning. The
language-model backbone remains frozen, while
attention LoRA adapters and the tied output
embedding adapt during
distillation. Training uses the highest-agreement tier from a transcript-consistency pipeline, followed by source reweighting during finetuning. On ten public Chinese–English
benchmarks, compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers reduces macro-average error from 5.61% to 5.27%. The 14-layer model reaches 5.75% with 20.7% fewer audio-tower parameters. Under the matched recipe, the 1.7B teacher yields 5.55% mean error, compared with 8.45% for self-
distillation, and progressive 18$\rightarrow$14
pruning outperforms direct
pruning (5.75% vs. 6.73%). These single-run results establish two practical operating points and show that the accuracy effects vary across
benchmarks. Project website: https://xpeng-ai.github.io/x-aut
Read the full abstract ▾
All authors Haojun Zhang, Yi Zou, Min Chen, Qize Yu, Lianrui Fan, Xini Ding, Hao Li, Shuchang Zhou, Xianming Liu, Shiyu Huang
Artificial Intelligence · Cross-listed from cs.CR
Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks
Guy Frankovits, Lior Yasur, Fred M. Grabovski et al. (+1 more)
This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and
video calls. Instead of passively searching for artifacts, DF-CAPTCHA
prompts the caller to perform simple challenge-response tasks that are easy for humans but difficult for current real-time deepfake systems to generate convincingly. The framework verifies the response using four criteria: realism, identity consistency, task completion, and response time. We evaluate the approach across both audio and
video modalities using user studies and experiments with real-time deepfake models. Results show that people often struggle to distinguish real-time deepfakes from authentic media, while DF-CAPTCHA substantially improves detection performance over passive methods, reaching high accuracy in both modalities. These findings suggest that active challenge-based verification is a practical and robust defense against next-generation social engineering attacks based on real-time deepfakes.
Read the full abstract ▾
All authors Guy Frankovits, Lior Yasur, Fred M. Grabovski, Yisroel Mirsky
Artificial Intelligence
From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment
Tabea Tietz, Torsten Schrade, Etienne Posthumus et al. (+4 more)
Cultural-heritage KGs such as the NFDI4Culture-KG contain millions of triples about artworks, music, inscriptions, historical events, and the people and places connected to them. For many users, however, discovering this knowledge can be difficult. While SPARQL can be learned, writing meaningful queries first requires an in-depth understanding of the graph's data model, an investment many domain researchers and practitioners are unwilling to make. Even with existing user interfaces, a starting point and some guidance are usually needed, because the data contained in the graph is highly specialized, heterogeneous, and constantly growing, making it challenging to know what it contains or which questions it can answer. In this paper, we present data stories as a way not only to lower this barrier, but also to turn exploration into data-quality assessment, and thus combine accessible querying with the discovery of issues that remain hidden in aggregate statistics. In this contribution, a data story is understood as a narrative document that integrates explanatory text and images with executable SPARQL queries and their visualized results. It is described how they are authored against the graph and how they serve several purposes: guiding users through an unfamiliar graph, creating reproducible narratives, and surfacing data-quality issues previously hidden in aggregate statistics. The authoring platform LODEON including its Sparnatural and AI-supported authoring assistants is introduced as a proof-of-concept. Within the authoring environment, every claim made about the data can be backed by an explicit query, making these narratives transparent and reproducible. This paper also reflects on lessons learned from hands-on seminars and workshops. Early experience suggests that such data stories make cultural-heritage knowledge graphs more accessible for both exploration and quality assessment.
Read the full abstract ▾
All authors Tabea Tietz, Torsten Schrade, Etienne Posthumus, Linnaea Söhn, Jonatan Jalle Steller, Jörg Waitelonis, Harald Sack
Artificial Intelligence
Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning
Bincheng Gu, Min Gao, Zongwei Wang et al. (+3 more)
Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the
reasoning capabilities of Large
Language Models (LLMs) on downstream tasks. Predictive
entropy provides a model-derived signal for such adaptation, guiding models toward higher-confidence
reasoning states without external verifiers or reward models. However, higher confidence does not necessarily imply correctness, as LLMs may remain highly confident along incorrect
reasoning trajectories. We observe that high-confidence
reasoning is more likely to be correct when confidence remains stable under local perturbations. Based on this observation, we propose Test-Time Adaptation via Stability-Aware Confidence Optimization (TASCO), a framework that incorporates local stability into confidence-based test-time adaptation while keeping the LLM frozen. TASCO operationalizes local stability by optimizing a lightweight task-level prefix under two alternative perturbation strategies: Random Perturbation promotes distributional stability across trajectories induced by nearby perturbed prefixes, whereas Sharpness-Aware Perturbation targets worst-case local sensitivity. Experiments demonstrate that TASCO improves
reasoning accuracy and
token efficiency across diverse LLMs and
reasoning benchmarks, while behavioral analyses show that it maintains stable confidence under local perturbations without prematurely concentrating the model's predictive distribution.
Read the full abstract ▾
All authors Bincheng Gu, Min Gao, Zongwei Wang, Yibing Bai, Yulan He, Junliang Yu
Artificial Intelligence · Cross-listed from cs.CY
Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling
Yongchao Martin Ma and Xinya Guan
Environmental controversies in global supply chains pose significant risks for global buyers. This study examines whether overseas suppliers' exposure to buyers' artificial intelligence (AI)-enabled environmental governance reduces supplier environmental controversies. Drawing on organizational information processing theory and signaling theory, we investigate how suppliers' exposure to AI-enabled governance influences their environmental controversies and the institutional contingencies under which this effect varies. Using text analysis to measure buyer AI-enabled environmental governance, we analyze panel data on 2,505 suppliers of U.S.-listed firms across 41 countries from 2020 to 2024 with multidimensional fixed-effects models. We find that suppliers' exposure to buyer AI-enabled environmental governance is negatively associated with supplier environmental controversies in the following year. This negative relationship is stronger in supplier countries with higher AI readiness and regulatory quality. The study contributes to research on AI-enabled sustainability governance and sustainable supply chain risk management.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents
Peiyuan Gao, Gaoyuan Zhang, Haojie Qin et al. (+5 more)
State-of-the-art
retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial
token costs. To reduce structural-context
tokens without compromising high RAG accuracy, we present VikingRAG, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round
retrieval. To further reduce
token overhead of multi-round interaction, we materialize agentic multi-round
retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce
token costs when agentic multi-round
retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented
retrieval when the evidence is sufficient, and invokes agentic multi-round
retrieval only otherwise. Experiments on real
datasets show that the base system VikingRAG matches high accuracy of state-of-the-art methods while consuming only 11.6%–51.9% of their
tokens. With
retrieval-trace reuse and adaptive escalation,
token costs drop to 5.1%–32.5% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.
Read the full abstract ▾
All authors Peiyuan Gao, Gaoyuan Zhang, Haojie Qin, Yahui Sun, Qianyi Zhang, Yunhao Zhang, Zeyu Wang, Wei Lu
Artificial Intelligence · Cross-listed from cs.SE
Agent-Integrated Software: Interaction Contracts and Continuous Assurance
Shengcheng Yu, Chunrong Fang and Zhenyu Chen
Embedding an intelligent
agent in an existing application creates a persistent coordination problem: users can revise goals and manipulate shared objects while delegated execution continues. We argue that dependable integration requires an explicit correspondence between task-level interaction and application behavior. We introduce
Agent-Integrated Software (AIS) as a software pattern combining a conventional core, direct interaction, and a built-in
agent, and Intent-Level Interaction Abstraction (IIA) as the task semantics through which users inspect and control delegated work. An open transition-system model relates AIS execution to IIA states and events. Interaction contracts constrain this relation through task bindings, role-specific authority, control transitions, and outcome evidence; continuous assurance maintains scoped claims as their dependencies change. A compact disclosure contract and conditional propositions illustrate why local component validity is insufficient and how selected admission invariants can be separated from planning. Contrasting software domains expose the framework's assumptions and limits. This perspective develops a research agenda spanning application abstraction, development support, controlled execution, quality assessment, and human supervision, with the aim of making
agent integration a maintainable software engineering discipline.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms
Pushpdeep Singh, Sayeh Jarollahi, Ayan Majumdar et al. (+5 more)
Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emergence of decentralized platforms with transparent, public moderation logs presents an unprecedented opportunity for independent audits. In this work, we leverage this architectural transparency to conduct the first large-scale audit of the default moderation system on Bluesky, the Bluesky Moderation Service (BMS). Analyzing its 10.6M moderation labels from 2025, we investigate three foundational aspects: (i) its mechanism (the degree of automation versus human oversight), (ii) its efficacy (accuracy in detecting harms), and (iii) its purpose (the landscape of harms it identifies). Our findings reveal a human-AI collaborative system where labels for sexual and graphic content are applied automatically in seconds, while nuanced and high stakes labels require more human oversight, taking hours or days. Through a manual annotation study, we find the BMS operates with high precision (0.837), but struggles with low recall (0.222), with our annotators identifying 4.5$\times$ more harmful content than the moderation system in a random sample. Finally, unsupervised clustering of the most frequently applied labeled posts uncovers detected harms ranging from hostility in discourse toward protected groups to the spread of sexually explicit and other graphic content. Our work offers a look into the operational realities of a deployed moderation system, providing a concrete data-driven foundation for designing more effective and transparent moderation systems.
Read the full abstract ▾
All authors Pushpdeep Singh, Sayeh Jarollahi, Ayan Majumdar, Vabuk Pahari, Abhijnan Chakraborty, Krishna P. Gummadi, Ingmar Weber, Abhisek Dash
Artificial Intelligence
RAMamba-Net: A Reliability-Aware and Mamba-Based Multimodal Fusion Network for Auditory Attention Detection
Xingyi He, Ziwei Wang and Dongrui Wu
Auditory
attention decoding (AAD) identifies the attended speaker from physiological signals, supporting neuro-steered hearing devices and natural human-machine interaction. Electroencephalography (
EEG) is the dominant modality for AAD but provides incomplete evidence in naturalistic audio-visual scenes, motivating
EEG and electrooculography (EOG) fusion. Existing approaches remain limited by weak cross-modal interaction, inefficient temporal modeling, and low robustness to sample variations. To address the limitations, we propose RAMamba-Net, a reliability-aware Mamba-based
multimodal fusion network for AAD. RAMamba-Net employs a Mamba-enhanced band-aware convolutional
Transformer to capture band-specific
EEG patterns and long-range temporal dynamics. A dual-branch temporal-spatial encoder models EOG temporal and inter-channel dependencies. Cross-modal
attention enables explicit modality interaction. Then, a reliability-aware module is introduced to estimate sample-wise modality weights for feature and prediction consistency, thereby enhancing
multimodal fusion. Experiments on two AAD
benchmarks demonstrate that RAMamba-Net effectively exploits complementary
EEG-EOG information, yielding accuracy gains of 5.76% over unimodal baselines, together with more robust decoding and discriminative representations. Further analyses show that explicit cross-modal interaction improves
multimodal alignment, while the reliability-aware module suppresses unreliable modality evidence and is robust to signal perturbation and parameter variation.
Read the full abstract ▾
Artificial Intelligence
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
Narcis Marincat
In shared-genome
language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high-performing globally visible model in the parent study learned an episode-entangled code. This companion study asks whether independently trained societies share one packet
language, where strict zero-shot transfer fails, and whether inherited interface state helps or harms later learning. First, a leakage-controlled causal interoperability audit over all 30 ordered pairs of six independently trained restricted societies – under sealed held-out structure and a preregistered raw/orthogonal/linear/nonlinear
alignment ladder – shows the six semantically similar interfaces do not form one raw
language: one same-initialization pair is exactly interoperable in both directions, a second shows asymmetric partial compatibility, and all 26 cross-initialization directions fail every frozen
alignment rung. Second, within the tested decomposition and a single sealed source formulation, a source-span control localizes strict zero-shot failure to interpretation and execution of the new operator instructions. Third, in a matched adaptation factorial, the globally trained communication interface acts as a severe negative-transfer prior: reinitializing only the packet reader, writer, and mouth raises final depth-three accuracy from 0.169 to 0.857. Fourth, across two restricted checkpoints and two independently frozen target streams each, inherited interfaces never exceeded fresh-interface controls by the preregistered 0.10 margin. All primary conclusions are bounded to a near-transfer 17-state setting; the negative-transfer factorial concerns one globally visible parent-cohort checkpoint, while an appendix adds a post hoc tagged-global twin case study.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNs
Camille Pradel
Knowledge graph foundation models such as ULTRA achieve zero-shot link prediction on unseen graphs through dedicated architectures that hard-code a transfer mechanism. In this work we move that mechanism out of the architecture and into the representation, by reifying the input graph: every fact becomes a node, connected to its subject, object, and relation type through a fixed vocabulary of six meta-relations, with relation types as anonymous shared nodes rather than model parameters. On this representation, five textbook GNNs (GAT, GINE with sum and with mean+max aggregation, GraphSAGE, R-GCN), each trained on a single knowledge graph of 4,245 triples for 30 minutes on one NVIDIA A100, transfer zero-shot to 40 inductive link-prediction
benchmarks. The best of them, an off-the-shelf GAT, matches ULTRA, a dedicated foundation model pretrained on three graphs, across ULTRA's own evaluation suite. The same fixed vocabulary extends to relational databases, a row becoming an entity and a foreign-key column a relation type; a preliminary probe on two unseen databases, with no
cell values, schema text or in-context labels, shows a model of this family pretrained on three knowledge graphs ranking foreign-key targets far above random-initialization and degree controls. We release the code, the checkpoints, and the evaluation pipeline for all 40
benchmarks.
Read the full abstract ▾
Artificial Intelligence
Ziwei Wang, Xingyi He, Hongbin Wang et al. (+3 more)
Multimodal brain state decoding has largely focused on fusing paired modalities for prediction, but has rarely explored how their correspondence can be further exploited to enrich training data and improve
multimodal representation learning. To address this gap, we propose CoMA-DiT, a bidirectional cross-modal
Diffusion Transformer for latent augmentation that treats paired modalities as sources of mutual generative supervision rather than merely as inputs to be fused. CoMA-DiT conditions velocity prediction on the paired modality through cross-modal
attention and adaptively injects the resulting variation via a reliability-gated residual mechanism. Experiments on
multimodal auditory
attention decoding and
emotion recognition showed that CoMA-DiT consistently outperformed 20 representative baselines, achieving absolute gains of 4.28% and 6.70% in accuracy and macro-F1 over the no-augmentation baseline, respectively. Extensive ablation, sensitivity, visualization, and interpretability analyses further demonstrated its robustness, generalizability, and ability to capture functionally relevant cross-modal interactions. These findings support a broader view of
multimodal learning: Paired modalities can serve not only as inputs for fusion but also as supervision sources that augment one another.
Read the full abstract ▾
All authors Ziwei Wang, Xingyi He, Hongbin Wang, Tianwang Jia, Bohan Fang, Dongrui Wu
Artificial Intelligence · Cross-listed from cs.CL
On the Impact of Anonymization on the Performance of Large Language Models
Tobias Deußer, Max Hahnbück, Lorenz Sparrenberg et al. (+3 more)
As large
language models are increasingly deployed in sensitive domains, anonymizing input data to protect personally identifiable information has become a critical practice. However, the impact of this anonymization on model utility is not well understood. This paper presents a systematic empirical study of the trade-off between
privacy and performance. We evaluate five prominent
language models across eleven diverse
benchmarks, comparing their performance on original versus pseudonymized inputs. Our results reveal that while anonymization generally degrades performance, the effect is highly nuanced. We find that more capable models, such as Qwen2.5-72B and GPT-4o mini, suffer the largest performance drops, suggesting a stronger reliance on specific entity information. The impact is also task-dependent: performance on TruthfulQA improves with anonymization, while
retrieval-focused tasks like RGB experience a catastrophic decline. Further experiments show that reversible anonymization techniques that preserve entity uniqueness significantly outperform irreversible ones like redaction, and that explicitly prompting models about anonymization offers no discernible benefit. We conclude that anonymization is not a one-size-fits-all solution and must be co-designed with the model and task in mind to balance
privacy and utility effectively. Our findings provide a crucial baseline for developing more robust,
privacy-aware AI systems.
Read the full abstract ▾
All authors Tobias Deußer, Max Hahnbück, Lorenz Sparrenberg, Tobias Uelwer, Christian Bauckhage, Rafet Sifa
Artificial Intelligence · Cross-listed from cs.CL
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and Natural Inference Datasets
Khloud AL Jallad, Nada Ghneim and Ghaida Rebdawi
Natural
Language Inference processes pairs of sentences to extract their semantic relations. NLI has been a hot research topic, integrated as a main component in other NLP applications. Despite significant advancements in textual inference across various
languages all around the world, Arabic
language still suffers from limited resources in this domain. To address this gap, this paper introduces E-CONAN
benchmarks that are composed of sentences pairs from various sources: (1) automatically-translated pairs, (2) human-validated machine-translated pairs, (3) hand-crafted pairs from teaching Arabic as foreign
language books, and (4) headlines pairs from different news channels containing rumors. E-CONAN contains two
benchmark datasets, E-CONAN-2, a 2-way
dataset (RTE) and E-CONAN-3, a 3-way
dataset (NLI). Additionally, we have used E-CONAN
benchmarks to evaluate 9 state-of-the-art
multilingual pretrained models using zero-shot classification. Models were evaluated across the ArNLI, XNLI, and E-CONAN
datasets. Results show that E-CONAN is a potentially valuable resource for evaluating model generalization and even for fine-tuning pre-trained models. Its diverse composition, derived from a combination of sources, offers a broader and more robust assessment compared to XNLI and ArNLI. In addition, we have evaluated 5 LLMs on E-CONAN-3
dataset. Moreover, we incorporated MARBERT as a representative Arabic-specific baseline and conducted performance evaluation comparison to demonstrate how Arabic-specific models scale against cross-lingual and LLM-based approaches on the E-CONAN
benchmarks. Furthermore, we conducted detailed qualitative and quantitative error analysis to analyze frequent error patterns. E-CONAN
benchmarks will be publicly available, we hope that it will enrich research community in Arabic textual entailment and natural
language inference.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LO
Rice's Theorem under Self-Modification: Elevation Operators and a Normal Form
Jose Pascual Gumbau Mezquita
We ask whether it can be certified algorithmically that a self-modifying program keeps a behavioural property, a safety property in the motivating case, after its next rewrite (preservation) and along its whole
evolution (persistence). When the rewrite depends only on behaviour, preservation is a behavioural property and Rice's
theorem applies. When the rewrite reads the code, preservation is no longer behavioural; yet, under a uniform disruption condition, the s-m-n reduction that proves Rice's
theorem works inside a single class of behaviourally identical programs, and preservation inherits the degree of the halting problem. One step never exceeds the degree of the property, while persistence can climb one level of the arithmetical hierarchy. We then isolate the mechanism shared by rewriting, supervision and system comparison, the elevation operator, and prove a normal form: the preserving set is determined by a single finite trigger and a polarity, and the Rice-Shapiro
theorem restricts the polarity to the arithmetical class of the property. Runtime monitors, consistency supervision, conformance to a reference and observational equivalence are instances, and no sound theory covers the preserving systems.
Read the full abstract ▾
Artificial Intelligence
AI Exposure and AI Resilience: A Two-Dimensional Assessment Framework for Software and Software-Based Business Model
Paul Darius Mandl, Peter Mandl and Martin Häusl
Artificial intelligence is changing both software production and the economics of software-based business models. Classical technology due diligence mainly examines technical properties such as architecture, scalability, and technical debt. These criteria do not fully capture how AI can affect a company's value proposition, competitive position, margins, or access to customers. This paper develops Artificial Intelligence Exposure and Resilience (AI-ER) as a two-dimensional assessment framework. AI exposure describes the pressure for change that AI creates for a business model. AI resilience describes the company's ability to absorb that pressure, adapt to changed conditions, and use AI in an economically viable way. Metrics for both dimensions are derived from current AI capabilities, their deployment conditions, and relevant research on business models and organizational adaptability. The model keeps exposure and resilience separate and adds an explicit assessment of evidence quality and confidence. It can be applied first with public information and later refined with internal evidence. The result is a traceable company profile that supports comparison without concealing uncertainty in the underlying evidence. The paper also specifies an initial score logic and a procedure for empirical validation.
Read the full abstract ▾
Artificial Intelligence
Magenta: Closing the Loop Between Mathematical Reasoning and Lean Verification
Joshua Ong Jun Leang, Haonan Li, Zheng Zhao et al. (+6 more)
Most of mathematical knowledge has been communicated through so-called informal use of mathematics and natural
language. With large
language models (LLMs) being highly adept in using natural
language, they achieve strong performance, yet not perfect, in informal mathematical
reasoning. Restraining LLMs to informal
reasoning misses out on the opportunity to use the discrete verification abilities that machines offer through machine-checkable proofs. In this paper, we bridge the gap between informal and formal
reasoning by integrating Lean signals into the informal
reasoning process. We introduce Magenta, a training-free agentic pipeline that, given only a natural-
language problem, produces an answer, expresses it as a Lean 4 statement, and constructs a machine-checked proof. A statement judge verifies whether the formalisation preserves the original problem, while an error-attribution judge routes failed attempts either to mathematical re-derivation or local Lean repair. Magenta achieves 100% accuracy across all evaluated olympiad
benchmarks, including AIME 2025, AIME 2026, and HMMT February 2026. When paired with the open-weight K2-Horizon-7B reasoner, it solves all six IMO 2026 problems. Our analysis shows that statement adjudication is essential for preventing false certificates and that feedback-guided correction outperforms independent resampling on difficult problems.
Read the full abstract ▾
All authors Joshua Ong Jun Leang, Haonan Li, Zheng Zhao, Xinyi Shang, Wenda Li, Zhengzhong Liu, Eric Xing, Shay Cohen, Eleonora Giunchiglia
Artificial Intelligence
Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents
Minghao Guo, Meng Cao, Sui Zhao et al. (+10 more)
Deep research
agents are increasingly capable of web search, tool use,
multimodal evidence analysis, and information synthesis. However, existing
benchmarks mainly evaluate medium-horizon exploration and rarely test whether
agents can sustain long, dependency-heavy research processes. We introduce Mr. LHDR (
Multimodal real-world Long-Horizon Deep Research), a
benchmark for evaluating real-world deep research over long, irreducible chains of interdependent evidence across eight categories. Each question is constructed from a hidden Node-Relation graph and requires an average of 12.1 necessary intermediate conclusions with a mean dependency depth of 10.4 before reaching a short, unique, and verifiable answer. Questions incorporate
multimodal evidence, including images, maps, PDFs, logos, charts, tables, and
video frames, with at least one non-text element that changes the
reasoning state. Mr. LHDR evaluates both final answers and the correctness of intermediate conclusions under annotated dependencies. We evaluate general models, deep research systems, and
agent frameworks using Overall Accuracy (OA), Strict Accuracy (SA), Checklist Score (CS), and Dependency-Aware Checklist Score (DACS). Results show that even the strongest system achieves only 43.1% OA and 34.3% SA, indicating that final-answer accuracy substantially overestimates complete research success. Removing images reduces DACS by 12.6 points, demonstrating the importance of
multimodal evidence, while SA consistently declines as
reasoning chains become longer. These findings reveal sustained, dependency-consistent evidence integration, rather than isolated fact
retrieval, as a key bottleneck for current deep research
agents.
Read the full abstract ▾
All authors Minghao Guo, Meng Cao, Sui Zhao, Siyu Ning, Xin Wang, Haoze Zhao, Jiaxuan Yang, Haihong Hao, Mingfei Han, Shunlin Rong, Haijun Wu, Xiaodan Liang, Xiaojun Chang
Artificial Intelligence
Routing by Reasoning Need: Trajectory-Aware Decoding Control for Diffusion Vision-Language Models
Yixiang Liu, Zhongxing Xu, Zhonghua Wang et al. (+1 more)
Diffusion vision-
language models generate answers through iterative refinement, exposing intermediate answer trajectories that can be inspected and controlled at inference time. However, this controllability creates a
reasoning-need mismatch, where a universal generation length is applied to questions with different
reasoning demands. Visually closed questions may be harmed by continued refinement after a stable answer has formed, whereas
reasoning-sensitive questions may be harmed by premature commitment. We formulate this problem as
reasoning-budget mismatch and study it in LLaDA-V. Rather than choosing a universal generation length, our training-free controller routes each example to early commitment, baseline preservation, or
reasoning-supportive decoding using trajectory signals from answer closure, commitment evidence, and representation revision pressure, without using ground-truth answers. Across answer-focused, mixed-
reasoning, and CoT-sensitive
benchmarks, routed control improves robustness over fixed long decoding, pure short decoding, and single-rule interventions. The gains are not explained by shorter outputs alone. Answer-closed examples often benefit from commitment, whereas CoT-sensitive examples require preserving or supporting intermediate
reasoning. Taken together, these results suggest
diffusion VLM decoding should route inference-time control by the state suggested by the observed trajectory instead of relying on a universal decoding length.
Read the full abstract ▾
All authors Yixiang Liu, Zhongxing Xu, Zhonghua Wang, Xiaoying Tang
Artificial Intelligence · Cross-listed from cs.CV
GRIPNet: Gaussian Radial Intensity Prior Guided Architecture for Pulmonary Nodule Detection in CT
Haojie Yang and Ran Su
Lung cancer causes more deaths than any other malignancy, and low-dose CT screening is the main pathway to early diagnosis. That pathway hinges on the smallest lesions, yet nodules below six millimeters remain hard to detect, because most methods treat a nodule as a generic object and ignore the imaging physics behind its appearance. We show that this appearance is highly regular. Intensity peaks at the
geometric center of a nodule and decays radially in a Gaussian pattern, and a fit to 18,218 annotated lesions from three public
benchmarks yields a mean radial coefficient of determination above 0.86 in every
dataset and size stratum. A square convolution samples both axes uniformly and is mismatched to this radial signal, most severely for small nodules. Guided by this evidence, we propose GRIPNet (Gaussian Radial Intensity Prior Network), a detector in which every module maps to a measurable property of the intensity distribution. Pinwheel convolutions decompose radial gradients, a dual-frequency module separates boundary detail from structural context, dilated masked
attention matches the decay extent, and an adaptive loss reweights samples by conspicuity. GRIPNet raises mAP@0.5 to 95.3, 91.6 and 97.9 percent on KanserSet, LUNA16 and Lung-PET-CT-Dx while sharpening high-IoU localization at real-time speed.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models
Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang et al. (+5 more)
We address few-shot object detection with
vision-
language models (VLMs) in out-of-domain settings such as aerial, industrial, and medical imagery, using only ten annotated images for supervision. Existing adaptation methods are discrete
prompt optimization and LoRA fine-tuning. We revisit a third option: soft prompting, where a small number of continuous
prompt tokens are optimized while the pretrained backbone remains frozen. We identify two key design choices. First, placing
prompt tokens at the cross-modal boundary between visual and text
tokens outperforms other placements (10.0 vs. 8.4 mAP). Second, initializing
prompts from the empty space
token outperforms semantic and random initialization. With these choices, one to three learned
tokens (7,168 parameters on average) match the best LoRA configuration on Roboflow20-VL (14.2 mAP, 10-shot) while training over 20,000x fewer parameters. Soft prompting remains harder to optimize, exhibiting higher variance across random seeds. Unlike LoRA, however, it causes no forgetting: the LoRA rank matching our accuracy reduces NaturalBench VQA accuracy by 35% relative, rising to 56% at the largest rank, whereas soft prompting leaves pretrained performance unchanged. The learned
tokens behave like
prompts rather than weights. They transfer to a newer model without retraining (+0.8 mAP on Qwen3.5-9B) and can be verbalized into readable
prompts competitive with
prompt-search methods (matching DetPO and outperforming GEPA). The approach also extends beyond detection. On RoboCasa manipulation tasks, the frozen $\pi_{0.5}$
vision-
language-action policy benefits from soft prompting, matching the LoRA baseline on two of three tasks when
tokens are placed at the gradient bottleneck. These results suggest modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask.
Read the full abstract ▾
All authors Gautam Rajendrakumar Gare, Siyi Li, Hewei Wang, Cesar Daniel Hernandez, Wei Zhao, Wolfgang M. Pauli, John Galeotti, Deva Ramanan
Artificial Intelligence · Cross-listed from cs.RO
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation
Yutong Hu, Fengjiao Chen, Xuezhi Cao et al. (+1 more)
Long-horizon
robot manipulation requires
memory, but not necessarily inside the action policy. To address such tasks, current agentic systems often combine VLAs with planners and
geometric tools, sometimes using additional depth or calibrated geometry. These systems confound attribution: gains may come from richer observations or alternative motor tools, while failures may stem from either the policy or an under-specified
language interface. We isolate this question through a deliberately constrained design: less tool breadth, but greater interface bandwidth. 2AM makes a
multimodal Agent the sole holder of task
memory and a single RGB-based, episodically stateless Action Model the sole executor of task-relevant motion. The
Agent compiles interaction history into subtask
language and optional 2D grasp, place, and move hints that bind its physical intention at different time scales. To teach this steerability to the VLA, we augment demonstrations with structured hint labels and train under condition dropout, spatial noise, and temporal jitter to tolerate imperfect
Agent outputs. On LIBERO-Mem, without depth, online geometry, or planner-based object motion, 2AM reaches 76.3% average completion, a 61.5-point improvement over the strongest reported baseline of 14.8%, together with 63.0% relaxed and 11.8% strict success. These results show that task
memory can remain
Agent-side. They further show that Action Model capability depends not only on what the policy has learned, but on how precisely the
Agent can steer it.
Read the full abstract ▾
All authors Yutong Hu, Fengjiao Chen, Xuezhi Cao, Renaud Detry
Artificial Intelligence
Memory Compression for High-Fanout Agent Sandboxes
Mengming Li, Ceyu XU, Qijun Zhang et al. (+4 more)
High-fanout
agent workloads create a growing
memory bottleneck because a single task may spawn many concurrent sandbox sessions. Yet these sandboxes are far from independent: they originate from a shared template and execute related trajectories, exposing substantial template-relative and cross-sandbox
memory redundancy. Conventional
memory compression is poorly matched to this setting in three fundamental dimensions: how to compress, because they fail to exploit similarity across non-identical sandbox pages; what to compress, because they control page-fault overhead through conservative page selection; and when to compress, because compression is either triggered by
memory pressure or performed without awareness of
agent execution phases. We present AgentZip, the first
memory compression system designed specifically for AI-
agent sandboxes. AgentZip introduces compression mechanisms that exploit both the template-relative and cross-sandbox redundancy. It broadens the compression scope to any page with a profitable representation and shifts overhead control from compression-time page selection to restore-time prefetching. It further aligns expensive compression with LLM waiting periods to avoid interfering with foreground tool execution. Across LLM training and inference workloads, AgentZip reduces sandbox-owned
memory by up to 8.7x, compared with 2.1x for the Linux configuration. Restore prefetching and
agent-execution-aware scheduling reduce the slowdown of aggressive compression from as high as 3.1x to 1.40x while retaining nearly all of its
memory-saving benefit.
Read the full abstract ▾
All authors Mengming Li, Ceyu XU, Qijun Zhang, Jiangnan Yu, Xiangfeng Sun, Haohui Mai, Zhiyao Xie
Artificial Intelligence
Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
Hyojung Han
We post-train Qwen3.8-27B for Korean response style – verbosity, list and markdown usage, discourse structure and register – and measure two behaviours the objective never targets: abstention on ambiguous social questions in KoBBQ, where the
benchmark-correct answer is UNKNOWN, and unprompted disclosure in securities guidance. Both move, and the changes are expressed primarily through the model's emission policy: how often it answers and how much it says. Matched target-form controls show that answer propensity depends on the training target, not the
prompt set or recipe alone. Holding
prompts, recipe, data volume and serving fixed and changing only the target text, three style seeds give positive answer-rate point estimates (mean +0.82 pp) and three neutral seeds negative ones (mean -1.53 pp); the observed seed ranges do not overlap and the means differ by 2.34 pp. A length-matched arm lies between them, and a fourth arm that stays short while preserving hedging is unstable across seeds, so which feature of the form is responsible is unresolved. For absolute stereotyped exposure the decomposition into an answer-propensity term and a conditional-composition term is an algebraic identity, not a finding; its empirical content is where the movement went. Across the trained checkpoints the changes are dominated by answer propensity while the composition term stays small, and because that term is evaluated on treatment-dependent answered subsets we do not read it as evidence about latent preference. Two measurement results follow. A between-arm contrast in conditional stereotyped share does not identify a change in conditional content preference when answer status is treatment-dependent. And agreement between two rule detectors for the same construct runs from 0.44 to 0.99 depending on which checkpoint produced the text – observable without any reference labels.
Read the full abstract ▾
Artificial Intelligence
Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data
Benjamin Gruenbaum, Doron Porat, Assaf Natanzon et al. (+4 more)
Synthetic relational data is normally produced by a model trained on a real
dataset, and its quality is measured as the distance to that
dataset. This paper describes a generator that has no real
dataset at either end. Given an industry, a company size, a business model, a set of business applications, and a random seed, it produces a complete fictional enterprise: a workforce, a customer base, sales deals, support tickets, recorded calls, chat messages, and documents, all consistent with one another. One entity graph is projected into the native formats of 66 business products, so the same customer appears in the CRM, the support desk, and the call system under one identity. Because no real counterpart exists, realism is built in from cited reference statistics and verified by reference-free measurement: a five-axis scorecard of 28 statistical checks, an
adversarial detector that hunts for the marks of synthetic generation, and a set of soundness checks that include a classifier test against an independently shuffled copy of the data. Because these instruments existed before the generator was tuned, progress is measured under a fixed yardstick: over 23 generated companies, mean realism climbed from 60.3 to 99.1, the weakest company from 41.1 to 94.9, and the detector, which initially flagged 55.2% of all records, now flags none. The scores hold on a seed never used during development. A second generator builds relational databases from a list of business questions. It forces qualifying rows for each answerable question, adds controlled near misses, and computes exact labels from the finished tables. The generator runs as a hosted service at https://console.era.eon.io. A company built there to a specification is served through its simulators over MCP and REST, and the simulators are also published as container images for offline use
Read the full abstract ▾
All authors Benjamin Gruenbaum, Doron Porat, Assaf Natanzon, Roy Zavida, Chen Dinachi, Or Itzahary, Omer Niv
Artificial Intelligence
When Does Text Inform? Benchmarking Information-Theoretic Metrics for Multimodal Time-Series Forecasting
Emma Andrews and Gianmarco Mengaldo
Multimodal forecasting models that combine time series with text annotations promise richer prediction through textual context, but how do we know whether a text annotation meaningfully contributes to the forecasters prediction? This is an information-theoretic question, but to evaluate whether information-theoretic metrics can reliably measure the predictive value an annotation provides, a ground truth
benchmark is needed, and none currently exist. We create a synthetic time series signal with annotations in three categories: semantically correct, incorrect, and irrelevant. Because the data generation process is fully controlled, ground-truth information content is known exactly, enabling principled evaluation of six complementary mutual information
estimators (KSG, MINE, InfoNCE, CCA, PID and V-information). We show that all six
estimators identify correct annotations as most informative, and are able to audit the quality of mixed text corpora, choosing the annotations that result in the best downstream
forecasting results without the need for model training. Our
benchmark identifies limitations of each
estimator, and these are validated on seven real-world
datasets, which show how
estimator performance differs on weak signals. Finally, we establish practical rules for implementing these metrics for annotation
auditing and fusion selection.
Read the full abstract ▾
Artificial Intelligence
Bio-inspired Learning and Decision-Making with Probabilistic In-Memory Computing Hardware: Part 1
Thomas Dalgaty, Eiji Kawasaki, Miguel de Prado et al. (+2 more)
Learning and decision-making in animals are often modeled as
Bayesian processes, where sensory evidence is integrated with prior beliefs to guide behavior in the face of uncertainty. But what are the inherent neural dynamics that give rise to this ability, and how could they be replicated in computing systems? This abstract discusses a biologically grounded framework in which noisy neural and synaptic dynamics perform inference and learning via
stochastic sampling from an internal energy function, capturing uncertainty over latent states and model parameters through neural and synaptic variability, respectively. This enables approaches such as predictive coding networks to account for epistemic uncertainty via Markov chain Monte Carlo sampling. Drawing a parallel between intrinsic noise in biological systems and electrical noise in emerging probabilistic analogue
memory technologies, we highlight how analogue in-
memory computing hardware naturally emerges as the solution for massively scalable and energy-efficient probabilistic inference.
Read the full abstract ▾
All authors Thomas Dalgaty, Eiji Kawasaki, Miguel de Prado, Devendra Vyas, Tommaso Salvatori