Artificial Intelligence
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
Han-Jun Ko, Jr-Jen Chen, Haobo Yuan et al. (+4 more)
Vision-
language models (VLMs) struggle to generalize in interactive physical
reasoning, particularly under unseen tasks and environments. Two key failure modes are prominent: hallucinated chain-of-thought (CoT)
reasoning that contradicts physical reality, and misalignment between the model's
reasoning and actions. We present VAORA (Visual Action Outcome
Reasoning Alignment), a novel reward design that directly addresses both issues. VAORA introduces two complementary rewards: Visual
Alignment Reward, which anchors VLM
reasoning to the visual context independent of the
agent action itself, and Visual-Action
Alignment Reward, which grounds
reasoning in the visual outcome induced by the model's action. Together, these rewards suppress hallucinated CoT and reduce the gap between
reasoning and behavior. To improve training stability, we further employ smooth, dense rewards by estimating success probabilities using a pre-trained in-domain expert
agent. Experiments on PHYRE and Virtual Tool support our performances across novel-task and unseen-environment settings, confirming that grounded and generalizable physical intelligence can be induced through VAORA.
Read the full abstract ▾
All authors Han-Jun Ko, Jr-Jen Chen, Haobo Yuan, Hsin-Ying Lee, Tiancheng Shen, Ming-Hsuan Yang, Yu-Chiang Frank Wang
Artificial Intelligence
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo et al. (+4 more)
Long-context LLM inference is increasingly limited by the
memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for
retrieval and multi-step
reasoning. We introduce FreqDepthKV, an inference-time cache compression method that factorizes adjacent-layer KV states into shared low-frequency depth components and sparse high-frequency residuals. A lightweight online probe assigns
attention heads to shared-depth, residual-depth, or exact cache modes according to their contribution to reconstruction-sensitive
attention logits, allowing the compression policy to adapt to
prompt structure without retraining. Across long-context question answering, needle
retrieval, summarization, and code generation
benchmarks, FreqDepthKV preserves task accuracy under substantially smaller cache budgets. With a 32k-
token prefill window, FreqDepthKV reaches 58.3 Exact Match, 63.0 F1, 32.5 ROUGE-L, and 48.1 pass@1, closely matching full KV while outperforming prior compressed-cache methods. It also improves decoding throughput to 70.4
tokens/s, reduces TTFT to 2.06 seconds, and lowers peak KV
memory to 6.2 GB, achieving a 3.9x effective compression ratio.
Read the full abstract ▾
All authors Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesús Olivera
Artificial Intelligence
FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games
Chase McDonald, Nathan Tsang and Wesley N. Kerr
We present FootsiesGym, an open-source environment for learning in a non-trivial two-player, zero-sum, imperfect-information game. Built on HiFight's minimalist 2D fighting game Footsies, it isolates the cyclic, non-transitive strategic interactions of fighting game neutral play while remaining simple enough for efficient analysis. We provide a vectorized simulator that enables high-throughput training on standard hardware, making the environment accessible and reproducible. We describe the design of the environment,
benchmark several reinforcement learning
algorithms, and discuss open research directions it enables. The code is available at https://github.com/como-research/FootsiesGym.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)
Kevin Xu and Alexander Quispe
GitHub hosts hundreds of millions of public repositories, but the platform exposes no native mapping from repositories to standardized industry sectors. This gap limits empirical work on the geography of innovation, the industrial composition of open-source production, and the
diffusion of new technologies across economic sectors. We present NAICS-GH, a publicly released corpus of 6,588 GitHub repositories drawn from source pools covering the United States, the European Union, and Australia, each labeled with a 2-digit sector from the North American Industry Classification System (NAICS 2022). Labels are produced by a retrieve-and-verify pipeline that combines BAAI/bge-large-en
embeddings, FAISS
retrieval, and GPT-4.1 rubric scoring. The pipeline narrows about 1.37 million source repositories to 31,178 candidate repository-sector pairs and retains 6,588 high-confidence labels with score at least 8. Re-running the
retrieval pipeline end to end reproduces the candidate set to within 0.03 percent. On a 2,421-repository human-validated random sample, the released labels attain 96.98 percent precision, with Wilson 95 percent confidence interval [96.23, 97.59]. We
benchmark six pretrained encoders on the released corpus; RoBERTa-large reaches 86.45 percent F1 and 86.35 percent accuracy on a held-out 20 percent test set. The
dataset, Croissant metadata, pipeline code,
prompts, and fine-tuned checkpoint are released under CC-BY-4.0 and MIT licenses.
Read the full abstract ▾
Artificial Intelligence
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
Qian Sun, Yong-Ming Tian, Jia-Wei Huang et al. (+2 more)
Recent years have witnessed the emergence of multivariate modeling using time series foundation models (TSFMs), which achieve advanced zero-shot generalization. Modern multivariate TSFMs are predominantly pretrained on multivariate synthetic data, which is easier to scale but may fail to capture the complex temporal dynamics and cross-variable relationships present in real-world time series. This raises a key question: Whether and to what extent the leading TSFMs trained with the real-world corpus perform better than those trained with synthetic data? To answer this, we establish the RMISC corpus, a considerably large-scale, high-quality, openly accessible, real-world, and multivariate time series archive that contains around 200
datasets and 142 billion time points across diverse domains. Furthermore, we pretrain four advanced TSFMs on univariate, synthetic multivariate, and real-world multivariate data and evaluate their zero-shot generalization capabilities on standard in-distribution and out-of-distribution
benchmarks. Experimental results show that incorporating real-world multivariate data predominantly improves the generalization performance for both univariate and multivariate TSFMs. These results provide a deeper understanding of how real-world multivariate data contributes to the development of stronger TSFMs.
Read the full abstract ▾
All authors Qian Sun, Yong-Ming Tian, Jia-Wei Huang, Cheng Feng, Shao-Qun Zhang
Artificial Intelligence
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Kai Ruan, Zihe Huang, Ziqi Zhou et al. (+4 more)
Large
language model (LLM)
agents often waste inference compute by continuing multi-step trajectories that are already doomed to fail. We study early failure prediction and inference-time early stopping for LLM
agents using hidden-state probes. Lightweight linear probes on internal activations predict eventual task failure from the first interaction round, substantially earlier than
agent-monitoring methods based only on observable behavior. We turn this signal into a recall-controlled abort cascade for reducing LLM
agent inference costs. The cascade applies a distribution-free calibrated failure detector at each early interaction round and jointly optimizes per-round recall budgets. This design ensures that eventually successful episodes survive all early-stopping gates at a user-specified global recall rate. After selection, the cascade is frozen and certified on independent data, providing an exact post-selection recall guarantee. We evaluate the method on TextCraft and WebShop with Qwen-2.5-7B, Llama-3.2-3B, and Qwen3-1.7B. The proposed LLM
agent early-stopping cascade outperforms the best single-gate baseline in every model-environment pair, saving 1.5-8.8 times more compute at a 90% recall target. Achieved recall remains within one standard deviation of its target in all 24 configurations. The strongest settings reduce generated
tokens by 60.2% on TextCraft and 54.9% on WebShop at 90% recall, while retaining savings of 45.0% and 41.5% at 95% recall. Behavior-only monitoring is consistently weaker, and adding behavioral features to hidden-state probes provides no further gain. We also characterize the sample complexity required to certify high-recall early-stopping policies. The code will be released soon.
Read the full abstract ▾
All authors Kai Ruan, Zihe Huang, Ziqi Zhou, Qianshan Wei, Jinghao Lin, Xuan Wang, Hao Sun
Artificial Intelligence · Cross-listed from cs.CL
Pitwall: Faithful Natural-Language Race-Strategy Briefings from a Calibrated Real-Time Monte Carlo Engine
Juan S. Santillana
Live sports commentary is grounded generation under a deadline: statements concern real, named athletes, the grounding state changes every few seconds, and no reference text exists at generation time. We present Pitwall, a production system that generates natural-
language Formula 1 strategy briefings in English, Spanish, and Portuguese, treating faithfulness as an architectural property rather than an aspiration: every published sentence is decomposed into typed factual claims (positions, gaps, tyres, pace, overtakes, race control) and each claim is verified against the probabilistic race state that prompted it. The same verifier gates the fine-tuning data: of 3,045 model-written targets, only the 81.9% whose every claim is state-supported are retained, the rest falling back to a provably faithful template, so the generator never sees an ungrounded target. Verification is meaningful because of the grounding substrate: a vectorized Monte Carlo engine (N=2,000 per-lap race continuations) calibrated on 126 races (2018-2024) and validated on fully held-out 2025-2026 seasons (winner-in-top-3 90.3% over 155 backtests; held-out Brier 0.0745). A recurring finding spans both halves of the system: virtues trade off and must be gated separately. In simulation, calibration-optimal is not decision-optimal; in generation, fine-tuning on richer targets buys vividness that collapses into
hallucination when the grounding state is sparse – a failure a four-base replication traces to base-model instruction adherence, not scale, and that sparse-context
auditing removes from the production model. End-to-end operation – live timing to verified trilingual briefings – was confirmed at two consecutive live Grands Prix (Austria and Britain, 2026); at Silverstone a timestamped probability trace, committed to disk before the outcome was known, locked onto the eventual winner ten laps before the flag.
Read the full abstract ▾
Artificial Intelligence
Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms
Marcos Eduardo Cruz Victorio and Karl Mason
The dairy industry in Ireland has a large potential for the integration of renewable energy and the reduction of carbon emissions. However, researchers of distributed generation control are mainly focused on residential and commercial applications. To contribute to the effective integration of renewable energy in the dairy sector, this paper presents a multi-objective optimisation control system based on differential
evolution and multi
agent Deep Reinforcement Learning. The proposed control is organised in two layers: the upper layer uses dynamic pricing, and the lower layer is based on multi-
agent reinforcement learning for battery management. This paper also simulates the electrical response of the proposed control system in a rural distribution
circuit. The simulation results show that the proposed control framework can improve profits from energy arbitrage up to 18% compared to using Rule-based models, increase the use of distributed generation without significantly increasing cost, and comply with the Irish grid code in terms of voltage variation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models
Cong Su, Jiaju Han, Xuemeng Sun et al. (+5 more)
Vision-
language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their
adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first
adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow
turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7–37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a
benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.
Read the full abstract ▾
All authors Cong Su, Jiaju Han, Xuemeng Sun, Chengyin Hu, Qike Zhang, Jiujiang Guo, Yiwei Wei, Jiahuan Long
Artificial Intelligence · Cross-listed from cs.CL
Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
So Hasegawa, Shailaja Keyur Sampat, Lei Liu et al. (+1 more)
Current
benchmarks for evaluating Large
Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact
retrieval from small tables and overlook the challenges of large multi-tabular
datasets, external knowledge integration, and exploratory insight discovery. We introduce DataGovBench, a
benchmark derived from governmental open data designed to evaluate LLMs in practical scenarios. The
benchmark includes two tasks: Table QA that requires solving complex decomposable questions and producing textual answers or visualizations, and Table Insight that evaluates the ability of models to generate expert-level findings through exploratory data analysis. Comprehensive experiments with state-of-the-art LLMs, both with and without agentic frameworks, reveal significant performance gaps across both tasks. These results suggest that current LLM-based systems remain far from satisfying the demands of real-world data analytics. DataGovBench provides a challenging
benchmark for advancing research on LLMs capable of both answering analytical queries and discovering insights from data. Code and sample data are available at https://github.com/SoHasegawa/datagovbench.
Read the full abstract ▾
All authors So Hasegawa, Shailaja Keyur Sampat, Lei Liu, Wei-Peng Chen
Artificial Intelligence · Cross-listed from cs.CV
Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation
Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo et al. (+4 more)
We present PACR-
Video, a parameter-efficient framework for multi-shot long
video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-
Video keeps a text-to-
video diffusion transformer frozen and augments it with low-rank temporal adapters conditioned by learned shot-role
prompt tokens. To maintain long-horizon coherence, it builds a recursive
prompt bank that stores compact entity, location, action, and style
prompts from previous shots, then routes them through adapter gates according to predicted narrative dependencies. A Shot-Local/Story-Global tuning objective combines next-shot reconstruction, cross-shot identity contrast, and
prompt sparsity regularization, while an adapter composition schedule balances early-shot visual consistency with later-shot event progression and viewpoint change. Across six multi-shot and long-
video benchmarks, PACR-
Video outperforms text-to-
video, tuning-based,
memory-augmented, streaming, and recursive-context baselines on distributional quality, semantic
alignment, identity consistency, temporal smoothness, motion stability, transition coherence, and human preference. These results show that compact
prompt routing and lightweight temporal adaptation provide sufficient controllable capacity for stable long
video extrapolation.
Read the full abstract ▾
All authors Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero, Julia Barrientos, Ainhoa Miranda, Jesús Olivera
Artificial Intelligence
A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems
Sonal Ankush Chibire, Jenn-Terng Gau and Bo Zhang
Physics-informed neural networks (PINNs) provide a promising framework for solving partial differential equations while
embedding the underlying physical laws directly into the learning process. This study presents a PINN-based framework for modeling transient elastodynamic wave propagation in bimaterial systems governed by the axisymmetric equations of linear elasticity. A steel-aluminum specimen representative of a Split Hopkinson Pressure Bar configuration is considered, and the governing elastodynamic equations, together with the corresponding initial, boundary, and interface conditions, are incorporated directly into the network through a physics-informed loss function. High-fidelity finite-element simulations performed using ANSYS Workbench Explicit Dynamics are used for validation and as supplementary data constraints during training. The proposed framework accurately predicts wave transmission and reflection across the bimaterial interface and reproduces axial and radial displacement histories, face-averaged responses, and the dominant stress and strain
evolution with close agreement to the finite-element solutions. The trained network further demonstrates the ability to predict wave responses at previously unseen time instants and for modified material properties without requiring additional finite-element simulations, providing a continuous surrogate model for elastodynamic analysis. Mesh-sensitivity studies confirm numerical robustness, while additional material combinations demonstrate the generality of the proposed methodology. The results show that integrating physics-informed neural networks with explicit finite-element analysis provides an accurate and computationally efficient framework for elastodynamic wave propagation in heterogeneous solids, offering an effective surrogate modeling approach for high-rate solid mechanics and impact engineering applications.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from quant-ph
Provable learning separation for predicting time-evolution of quantum many-body systems
Rahul Bandyopadhyay, Riccardo Molteni, Jens Eisert et al. (+2 more)
Given that
quantum computers are naturally suited to simulate the behavior of
quantum many-body systems, an immediate question arises: can one formulate physically motivated
quantum machine learning (QML) tasks that exhibit learning separations? We address this problem by studying the learnability of
quantum many-body dynamics from the perspective of probably approximately correct (PAC)-learning. Concretely, we devise a supervised learning problem where the training set consists of specifications of randomized stabilizer probe states,
evolution times sampled uniformly from a polynomially large time interval $[0,T]$, coupled with expectation values of certain observables evaluated on the resulting time-evolved state under an unknown
Hamiltonian. For this learning task, we provide an efficient
quantum procedure whose training phase learns the underlying
Hamiltonian from short-time training samples, and whose deployment phase combines
Hamiltonian simulation with the classical shadows protocol to perform inference on a newly given data point. By contrast, the existence of $O(\mathsf{poly}(n))$-time instances ensures classical hardness: by
embedding a $\mathsf{BQP}$-complete computation into the polynomially long time-dynamics of a low-intersection variant of the Feynman-Kitaev clock
Hamiltonian construction, we show that, for a certain family of input distributions, no randomized classical
polynomial-time
algorithm can fulfill our learning condition, unless $\mathsf{BQP}\subseteq\mathsf{P/poly}$. Furthermore, we show that the classically hard instance maintains
quantum learnability. We also give an interpretation of our results in learning-assisted certified
quantum simulation. Taken together, our results demonstrate a rigorous learning separation for a natural ML task based on
Hamiltonian evolution, while building connections between
quantum learning theory,
quantum simulation, and QML.
Read the full abstract ▾
All authors Rahul Bandyopadhyay, Riccardo Molteni, Jens Eisert, Vedran Dunjko, Sofiene Jerbi
Artificial Intelligence · Cross-listed from cs.CL
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
Taeyun Roh, Eunha Lee, Wonjune Jang et al. (+3 more)
Biomedical question answering requires not only accurate extraction of information from scientific literature but also reliable integration of evidence across multiple documents. This study presents a question-type-specific large
language model (LLM) framework for BioASQ 14b Task B, designed to improve answer robustness and evidence grounding in biomedical question answering. Rather than applying a single prompting strategy to all questions, the framework selects different inference procedures for yes/no, factoid, and list questions according to their distinct
reasoning and evaluation requirements. For yes/no questions, snippet shuffling and self-reflection are used to reduce sensitivity to evidence ordering and improve decision stability. For factoid questions, full-snippet input is combined with chain-of-thought-based in-context learning to support accurate biomedical entity identification. For list questions, a multi-
agent architecture is employed, in which evidence extraction, candidate generation, answer verification, and final aggregation are handled collaboratively. Preliminary experiments on BioASQ 13b were used to identify effective inference strategies for each question type, and the resulting framework was subsequently evaluated in the official BioASQ 14b Task B challenge. In the official evaluation, our framework showed competitive performance across multiple batches and achieved first place in the factoid subtask of Batch 4. These results demonstrate the effectiveness of combining question-type-specific inference, ensemble prediction, and
agent-based verification for reliable biomedical question answering.
Read the full abstract ▾
All authors Taeyun Roh, Eunha Lee, Wonjune Jang, Sohyun Chung, Junha Jung, Jaewoo Kang
Artificial Intelligence
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Jihao Liu, Guoxiong Gao, Zeming Sun et al. (+8 more)
Recent LLM-based mathematical
reasoning agents have begun to tackle research-level problems and, in several cases, have contributed to the resolution of open problems. However, scaling and orchestrating such
agents effectively remains challenging, due to the difficulty of coordinating parallel proof search while keeping intermediate claims organized and reliable. In this paper, we propose Danus, an orchestration system for research-level mathematical
reasoning centered on a shared fact graph as a global
memory-management mechanism. Danus consists of a main
agent that performs planning and coordination, multiple worker
agents that carry out proof search in parallel, and a stateless verifier that checks proposed mathematical claims before they are admitted into the fact graph. Each verified fact is stored together with its proof and logical dependencies, allowing the system to build long arguments incrementally while keeping the shared proof state organized. The main
agent periodically summarizes the evolving proof state, redirects workers across promising directions, and supports interaction with human mathematicians through progress reports. We evaluate Danus through six research-level case studies in algebraic geometry, singularity theory, and combinatorics, illustrating how the fact-graph
memory mechanism enables Danus to construct long, detailed mathematical proofs. Our results suggest that fact-graph-based orchestration provides an effective route toward scaling mathematical
reasoning agents for long-horizon research problems. Danus is open source at https://github.com/frenzymath/Danus.
Read the full abstract ▾
All authors Jihao Liu, Guoxiong Gao, Zeming Sun, Bin Wu, Shurui Liu, Jiedong Jiang, Haocheng Ju, Leheng Chen, Ronnie Cheng, Xiping Zhang, Bin Dong
Artificial Intelligence · Cross-listed from cs.CV
Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
Yoav Baron, Sara Dorfman, Roni Paiss et al. (+2 more)
Vision-
Language Models (VLMs) are increasingly utilized as the conditioning backbone for
diffusion-based image editing due to their remarkable
multimodal reasoning capabilities. While standalone VLMs demonstrate strong localization capabilities, editing pipelines frequently struggle to maintain this accuracy, particularly in complex, multi-entity scenes. In this work, we investigate this performance gap, hypothesizing that it stems from treating the VLM as a condition encoder. In this role, the model is restricted to a single forward pass, preventing the autoregressive generation process for which it was optimized, thereby failing to fully expose its capabilities. To investigate whether this spatial understanding persists when the VLM is used as a condition encoder, we introduce Analysis-by-Proxy. In this framework, we train a lightweight, interpretable proxy model on the VLM's intermediate representations using an auxiliary localization task. By analyzing the VLM through this proxy, we uncover the specific VLM representations that encode localization information. Our findings expose a fundamental mismatch between how spatial knowledge is represented within a VLM condition encoder and how it is extracted by current editing pipelines. We reveal that under single-pass constraints, the localization signal does not reliably propagate to the predefined layer configurations commonly used for conditioning. Instead, this crucial signal remains hidden within intermediate representations, at locations that vary depending on the input
prompt. Using our introduced Analysis-by-Proxy framework, we reveal the fundamental failures of existing condition extraction strategies in editing pipelines, opening the door to more principled design of conditioning architectures.
Read the full abstract ▾
All authors Yoav Baron, Sara Dorfman, Roni Paiss, Daniel Cohen-Or, Or Patashnik
Artificial Intelligence
Trust but Verify:Evidence-Linked Multi-Agent Clinical Information Extraction in Pathology
Yufan Wang, Anit Kumar Sahu, Yan Fei Ng et al. (+8 more)
Clinical feature extraction from pathology reports is challenging because relevant evidence may be distributed across coded and narrative fields and depend on specimen attribution, negation, ancillary findings, and diagnostic context. We retrospectively evaluated the NimbleMind Multi-
Agent System (nMAS), a configurable workflow that separates clinician-defined field specifications from extraction models and returns report-level predictions with source-linked evidence. The study included 54 dummy gastric biopsy pathology reports from Singapore and four binary target fields, yielding 216 feature-case decisions. nMAS correctly classified 213 of 216 decisions (98.61%), and all evidence spans associated with correct predictions occurred verbatim in the corresponding source reports. All three errors occurred in the two context-dependent H. pylori-related fields requiring negation handling or diagnostic attribution. A single-model UMA-style comparator produced the similar label-level performance and error pattern. These findings do not demonstrate predictive superiority for the multi-
agent architecture.Rather, the contribution of nMAS lies in workflow integration and traceability through configurable field specifications, complexity-based routing, report-level aggregation, and source-text validation within a clinician-reviewable workflow. Larger multi-institutional studies should assess generalizability, semantic evidence quality, adaptation effort, and clinician verification time.
Read the full abstract ▾
All authors Yufan Wang, Anit Kumar Sahu, Yan Fei Ng, Daniel Kang, Shayan Vassef, Soorya Ram Shimgekar, Koustuv Saha, Piyum Zonooz, Navin Kumar, Chee Leong Cheng, Li Yan Khor
Artificial Intelligence · Cross-listed from cs.LG
TILDE: TILt-based Distributional Erasure for Concept Unlearning
Naveen George, Naoki Murata, Yuhta Takida et al. (+2 more)
Concept unlearning in text-to-image
diffusion models is critical for safe and practical deployment: with rising
privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional
alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each
prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained
diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.
Read the full abstract ▾
All authors Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji
Artificial Intelligence · Cross-listed from cs.CV
HoloCount: A Holistic Visual Counting Benchmark for MLLMs
Jinhong Deng, Limeng Qiao and Guanglu Wan
Visual counting is a fundamental pillar of
multimodal intelligence, requiring a seamless integration of fine-grained grounding and spatial
reasoning. While
Multimodal Large
Language Models (MLLMs) have achieved remarkable success in qualitative scene understanding, their quantitative precision remains a significant bottleneck, often characterized by persistent numerical
hallucinations. Existing counting
benchmarks primarily focus on basic perception in simplified contexts, failing to capture the complex failure modes that emerge under logical constraints or
adversarial conditions. To address these limitations, we introduce HoloCount, a holistic and diagnostically rich
benchmark structured around a three-level hierarchical taxonomy. HoloCount evaluates MLLMs across: (1) Semantic Counting, focusing on atomic and property-based enumeration; (2) Analytical Counting, assessing logical composition through spatial and set-based
reasoning; and (3) Robustness Testing, probing model integrity against adverse scenarios and grounded counter-priors, such as high-density scenes and linguistic biases. Through an exhaustive evaluation of over 20 state-of-the-art MLLMs, we reveal a critical performance gap: even top-tier models degrade significantly as tasks transition from perception to complex analytical
reasoning and adverse scenarios. Our findings provide a systematic landscape of current MLLM counting capabilities and offer a roadmap for developing more grounded and reliable
multimodal systems. The
dataset is available at https://mm-mvr.github.io/HoloCount/.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ME
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
Hao He, Xueying Liu, Chris J. Kuhlman et al. (+1 more)
Large
language model coding
agents increasingly perform open-ended data modeling and analysis. These
agents are
stochastic and adaptive, and therefore their autonomous model discovery behavior cannot be adequately characterized by a single
benchmark run. In this work, we propose an experimental design and analysis framework for systematically evaluating this discovery process, quantifying its variability, and identifying important factors. The proposed framework treats these
agents as
stochastic model-discovery operators, which map task-specific discovery data and an optimization target to a fitted model. Specifically, we investigate two such operators, Codex and Claude Code, under controlled experimental factors including
agent's
reasoning effort, task, optimization metric, and composition of training data. For each
agent-task-metric combination, regression models and inference are conducted for multiple responses such as output quality, dollar cost, wall-clock time, and process complexity. Furthermore, we develop a utility-aligned canonical decomposition to characterize the dominant direction of the
reasoning-effort effect and to assess whether that direction aligns with a performance-cost utility direction. The proposed framework is demonstrated on a testbed of networked word-forming games with insightful findings on
reasoning effort with respect to cost and process complexity.
Read the full abstract ▾
All authors Hao He, Xueying Liu, Chris J. Kuhlman, Xinwei Deng
Artificial Intelligence · Cross-listed from cs.SE
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications
Evgeny Shilov
Developers increasingly delegate real maintenance work to product-grade coding
agents, and many state tasks in their native
language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a
benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian – written from scratch, not translated – and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks.
Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently substituting the model on 20% of tasks via an official safeguard fallback – evidence that the deployed product, not the model, is the unit actually measured. Version 2 adds Round 2: seven further configurations on the same frozen set under a per-configuration freshness gate – the Russian-
market agents SourceCraft CLI (ds, legacy) and Koda CLI (koda-pro), Antigravity with Gemini 3.1 Pro and 3.5 Flash, and Codex CLI with GPT-5.6 Sol and Luna. SourceCraft's flagship resolves 68.1% (N=23), above GPT-5.5 and both Gemini rows. A tool-call contamination re-audit of all 437 Round-2 trajectories finds the Russian and Gemini columns clean (0/293
cells) while flagging systematic oracle-hunting in the GPT-5.6 family (8/69 and 13/75
cells), including one case of mining a prior round's artifacts from the run machine's disk; honest scores are published alongside raw ones. We release statements, metadata, trajectories, and diffs; oracles are withheld with a SHA-256 manifest.
Read the full abstract ▾
Artificial Intelligence
ExplAIner: A Declarative Query Language for Explaining Classification Models
Marcelo Arenas, Pablo Barceló, Diego Bustamante et al. (+3 more)
The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proliferation of explanation notions calls for declarative query
languages in which such notions can be specified, combined, and analyzed uniformly. In this paper, we develop such a framework for Boolean models. We first revisit FOIL, an interpretability query
language for black-box models, and show that it has two fundamental limitations: it cannot express central optimality-based explanation queries, and its evaluation problem over decision trees is hard for every level of the
polynomial hierarchy. We then introduce ExplAIner, a query
language based on FOIL with an extended vocabulary and a layered structure. We show that ExplAIner can express a broad family of explanation notions, including abductive, contrastive, feature-based, and distance-based queries. We also prove that the evaluation problem for each query in ExplAIner belongs to the Boolean hierarchy over every class of Boolean models for which some basic predicates can be evaluated in
polynomial time. In particular, that property holds for deterministic and decomposable Boolean
circuits. Finally, we introduce Opt-FOIL, an optimization-oriented fragment of ExplAIner for computing explanations that are minimal with respect to strict partial orders, and prove that its evaluation problem is in $\mathrm{FP}^{\mathrm{NP}}$ under the same tractability assumptions. These complexity results have a direct algorithmic consequence: a fixed ExplAIner query can be evaluated with a fixed number of calls to a SAT solver, while a notion of explanation specified in Opt-FOIL can be computed with a
polynomial number of such calls. This is particularly relevant in formal XAI, where SAT solvers have been successfully used to compute explanations for several classes of ML models.
Read the full abstract ▾
All authors Marcelo Arenas, Pablo Barceló, Diego Bustamante, Jose Caraball, María Alejandra Schild, Bernardo Subercaseaux
Artificial Intelligence · Cross-listed from cs.CV
What Images Cannot Say: Language-Guided Olfactory Representation Learning
Eleftherios Tsonis, Xi Wang and Vicky Kalogeiton
Images tell us what a scene looks like, but rarely what it would feel like to be there. While recent
datasets pair visual scenes with electronic-nose measurements, aligning smell signals with images remains challenging because many olfactory cues arise from contextual environmental factors that are not directly visible in pixels. We introduce SCENT, a
multimodal framework that uses
language guidance as a semantic bridge between
vision and olfaction. Our approach leverages
Vision-
Language Models (VLMs) to generate scene descriptors capturing objects, environmental context, and plausible ambient smell cues suggested by the visual scene. These descriptors provide semantic guidance for learning olfactory representations. We train a smell encoder that maps electronic-nose signals into a shared
embedding space aligned with both visual and textual representations, and introduce a languageguided latent decomposition that separates object-specific odors from contextual environmental contributions. Experiments on the New York Smells
dataset demonstrate that SCENT significantly improves crossmodal
retrieval compared to
vision-only baselines, achieving state-of-theart performance on smell-to-image and smell-to-text
retrieval tasks. In addition, our framework produces interpretable olfactory representations that enable the disentanglement of complex smell mixtures. Our results reveal the importance of contextual semantic information for grounding olfactory perception in
multimodal learning and pave the way for future research in this area.
Read the full abstract ▾
Artificial Intelligence
A Definition and Roadmap for World Models
Xinyuan Chen, Haoyu Guo, Shi Guo et al. (+10 more)
World models – internal simulators that learn the structure and dynamics of an environment – have become one of the most actively debated concepts in AI. From model-based reinforcement learning and
video generation to
embodied robotics and ultimately, physical AI, researchers across AI subfields are building systems that they call "world models", yet there is no consensus on what a world model fundamentally is, what it should predict, or how it should be built. This perspective article provides a scientific definition of world models, discussions of their key technical aspects, and a staged roadmap for developing effective world models.
Read the full abstract ▾
All authors Xinyuan Chen, Haoyu Guo, Shi Guo, Bingqi Jiang, Chunhua Shen, Xing Shen, Tianfan Xue, Yufei Xue, Mulin Yu, Weinan Zhang, Bin Zhao, Bowen Zhou, Ming Zhou
Artificial Intelligence
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
Xiachong Lin, Du Yin, Arian Prabowo et al. (+6 more)
Building sensors are embedded in physical
topology, spatial hierarchy, and operational context, yet existing forecasters often treat them as isolated time series or rely on fixed
covariate sets. We present TopoBrick, a training-free framework for zero-shot building IoT (Internet-of-Things)
forecasting. TopoBrick uses building knowledge graphs to construct a compact structural skeleton and employs an agentic
topology sampler to select target-specific exogenous variables. The selected variables are organized by deployment-time availability, separating past-known sensor states from future-known calendar, schedule, and meteorological exogenous variables. Across three real-world buildings, TopoBrick outperforms strong zero-shot foundation-model baselines and remains competitive with fully trained building-specific models. Ablations show that
topology-aware sampling is more reliable than random, ontology-only, or fixed-hop selection, especially for physically coupled HVAC and weather-driven sensing variables.
Read the full abstract ▾
All authors Xiachong Lin, Du Yin, Arian Prabowo, Hao Xue, Wen Hu, Imran Razzak, Matthew Amos, Sam Behrens, Flora D. Salim
Artificial Intelligence · Cross-listed from cs.RO
Responsible Personalisation: The Double-Edged Sword of Personalisation in Human-Robot Interaction
Antonio Andriella, Jauwairia Nasir, Andrea Rezzani et al. (+7 more)
While personalisation is becoming a defining capability in human-
robot interaction (HRI), the existing literature on responsible personalisation remains fragmented, offering isolated accounts of ethical risks without a structured understanding of how they emerge across interaction contexts. This gap is particularly critical in HRI, where
robots' embodiment and social presence can amplify and reshape such risks or generate new types of risks. We present a lifecycle-based and context-sensitive framework for personalised HRI, grounded in an embodiment-aware perspective. The framework combines stages of the personalisation process with interaction characteristics (short-term vs. long-term, open-domain vs. closed-domain), enabling systematic analysis of how risks arise and evolve. Building on this, we conduct an integrative analysis of key ethical risks, including autonomy erosion, biased user modelling, manipulation, dehumanisation, and
privacy violations, and examine how they manifest across contexts. We translate these insights into actionable design recommendations and outline open research challenges. By structuring both the design space and risk landscape of personalised HRI, this work provides a foundation for more systematic, transparent, and ethically grounded approaches to personalised
robot behaviour.
Read the full abstract ▾
All authors Antonio Andriella, Jauwairia Nasir, Andrea Rezzani, Alyssa Kubota, Dimitri Lacroix, Tamlin Love, Aniol Civit, Vicky Charisi, Elisabeth Andre, Wing-Yue Geoffrey Louie
Artificial Intelligence · Cross-listed from cs.FL
Harnessing Code Agents for Automatic Software Verification
Shuangxiang Kan, Shuanglong Kan and Sebastian Ertel
Formal verification offers the strongest guarantee of software correctness, but it does not scale: the proofs demanded by interactive
theorem provers such as Coq require enormous expert effort. Large
language models (LLMs) promise to generate these proofs automatically, yet existing approaches wire a fixed, human-designed proof strategy into the system and constrain the model to follow it (retrieving premises and predicting tactics one step at a time, or splitting goals by divide-and-conquer), and still prove only a fraction of their target
theorems. We show that imposing such a strategy is unnecessary and limiting. Handing the whole lemma to a general LLM code
agent (for example, Claude Code), free to choose its own approach, and wrapping it in a verification harness is both simpler and more effective, achieving full coverage: every targeted lemma proved, with no failures and no Coq expert intervention. The
agent writes the proofs under feedback and hard constraints from the harness that keep each one sound (accepted only when the prover's kernel closes it), complete (no obligation left unproved or silently dropped), and terminating (no divergent tactics). We evaluate this harness plus code
agent along three dimensions. (1) Core logic: on Iris, the state-of-the-art separation logic for concurrent and
memory-manipulating programs, Aria proves all 4,257 lemmas of the four core modules and the 217 lemmas verifying Rust's standard libraries built on it, fully automatically. (2) Comparison with prior LLM provers: on reglang, where prior provers manage barely one in eight, Aria proves all 318. (3) Generality: on iris-lean, the unfinished Lean 4 port of Iris, it proves 72 not-yet-ported lemmas, showing the approach is not specific to Coq. A state-of-the-art model (Claude Opus 4.7) can write proofs for verified software development fully and automatically.
Read the full abstract ▾
Artificial Intelligence
Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models
Franz Motzkus and Sebastian Bernhard
The increasing adoption of end-to-end learning for autonomous driving introduces increased model complexity and opacity, raising the risk of learning undesired or erroneous behavior. In this work, we integrate unsupervised dictionary learning as a post hoc interpretability module within state-of-the-art driving models to decompose driving behavior into semantically meaningful concepts while demonstrating their causal influence on the model's driving decisions. We propose a stepwise framework for extracting and interpreting meaningful concepts from the end-to-end model and connecting them to the multifaceted model outputs, thereby revealing the underlying decision-making logic for the prediction of future trajectories. Furthermore, targeted interventions at the concept level allow us to manipulate and correct driving decisions, resulting in measurable improvements in overall driving performance. We thus demonstrate how interpretability can effectively be used to reduce model opacity, uncover erroneous behavior, and enable targeted mitigation, ultimately boosting model performance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
Andrea Alfarano, Andrea Bacciu, Saab Mansour et al. (+2 more)
Uncertainty estimation (UE) enables LLM-powered systems to recognize when to abstain, yet existing research has predominantly focused on English. We present the first large-scale evaluation of UE methods across 22
languages, spanning high-, mid-, and low-resource settings. Using two human-curated Q&A
datasets, we compare open and closed box UE methods (nine in total) across different model sizes and architectures while eliciting long-form
reasoning, avoiding LLM-as-a-judge and
embedding-based scoring, which can introduce evaluation noise. We report three main actionable findings. First, we find that prompting models to reason in English while keeping questions in low-resource
languages substantially improves UE performance, suggesting that comprehension of low-resource
languages is largely intact, and that the reliability bottleneck lies in generation rather than understanding. Second, prompting models to reason in English closes the UE performance gap between low and high-resource
languages, demonstrating that generation
language matters more than the question
language. Third, the choice of UE method should depend on model scale: at smaller scales, open-box probability-based methods outperform alternatives; at larger scales, closed-box self-verbalized uncertainty becomes superior. Finally, we provide an analysis of threshold selection for selective prediction, offering guidance on calibrating abstention in
multilingual settings.
Read the full abstract ▾
All authors Andrea Alfarano, Andrea Bacciu, Saab Mansour, Amin Mantrach, Marcello Federico
Artificial Intelligence
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail
He Liu, Changtao Miao, Xinjie Yang et al. (+12 more)
Large
language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. Existing guardrails face a practical trade-off between lightweight classification-based models, which are efficient but often struggle with concealed intent, ambiguous semantics, and borderline safety decisions, and
reasoning-based guards, which improve judgment quality but introduce additional
token generation and inference latency. We present DT-Guard, a content safety guardrail model based on a
Reasoning-Active Training,
Reasoning-Free Inference paradigm. The key idea is to use
reasoning supervision during training while emitting only structured safety labels at inference time. DT-Guard formulates safety judgment as a progressive decision process, Intent - Category - Safety, and constructs an intent-driven
dataset with intent labels, risk categories, safety labels, and structured
reasoning trajectories. To further improve hard-case robustness, we propose Rollout-Guided Progressive Hard-Case Optimization (RG-PHO), which uses multi-rollout consistency to identify stably mastered, persistently failed, and preference-unstable samples, and applies targeted supervised and preference optimization accordingly. At inference time, DT-Guard directly generates structured labels without explicit
reasoning traces, preserving deployment efficiency. Experiments on
prompt-side and response-side safety
benchmarks show that DT-Guard achieves average F1 scores of 0.886 and 0.870, respectively. With only a 4B backbone, it reaches a dual-side average F1 of 0.878, outperforming strong 8B guardrail baselines. These results demonstrate that
reasoning supervision can be effectively internalized into low-latency safety discrimination.
Read the full abstract ▾
All authors He Liu, Changtao Miao, Xinjie Yang, Tianle Song, Yin Wu, Junchi Chen, Bintao He, Xinyuan Zhang, Bo Zhang, Shi Yan, Wei Lu, Wei Wang, Danyang Xu, Jiansheng Cai, Zhe Li