Artificial Intelligence
VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences
Yiwen Jiang, Yang Deng, Stephanie Fong et al. (+9 more)
Personalized Large
Language Models (PLLMs) aim to tailor responses to individual users, where a central challenge is preference
reasoning: inferring query-relevant preferences from user-related history. Existing
benchmarks, however, largely assume that such preference can be retrieved from semantically related history. We study an underexplored but practically important regime, profile-preference conceptual misalignment (PRCM), where observable profile cues and query-specific preferences lie in different concept spaces, making semantic
retrieval inconsistent for personalization. We introduce VIBE-Bench, a
benchmark with two psychology-grounded tasks, 3,504 personas and 12,239 dialogues, including a manually verified gold test set, and requires cross-concept preference
reasoning beyond surface semantic overlap. Experiments with several personalization methods show that current PLLMs largely rely on shallow semantic correlations and fail to acquire robust cross-concept mappings. These findings establish PRCM as a distinct failure regime in PLLMs and position VIBE-Bench as a focused testbed for advancing preference
reasoning beyond semantic matching.
Read the full abstract ▾
All authors Yiwen Jiang, Yang Deng, Stephanie Fong, Zimu Wang, Yaling Shen, Wei Feng, Hongxi Yang, Xiangyu Zhao, Zhongxing Xu, Deval Mehta, Xuelian Cheng, Zongyuan Ge
Artificial Intelligence
RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation
Zhongru Chen, Yuan Wu and Yi Chang
Large
language models are increasingly used as interactive recommender assistants. Their evaluation should therefore go beyond plausible item recommendation and test whether they can recognize flawed recommendation requests. Existing recommender
benchmarks mainly assess ranking, generation, or preference satisfaction, while existing error-detection
benchmarks are usually not grounded in recommendation-specific user and candidate evidence. To address this gap, we introduce RPCBench, a
benchmark for evaluating Recommender-Premise Critique: the ability to detect, diagnose, and properly handle faulty premises in natural-
language recommendation requests. RPCBench contains evidence-grounded test instances from five recommendation domains and covers ten types of premise failures. Each instance provides a visible recommendation context and a corrupted user query. We further design a fine-grained evaluation framework that measures proactive detection, error localization, post-detection handling strategy, and evidence faithfulness. Through a systematic evaluation of 11 LLMs, we find that proactive detection is the main bottleneck in Recommender-Premise Critique, and models perform worst on underspecified-premise errors. We also observe that target-critical information density matters more than redundant evidence, and that longer
reasoning does not monotonically improve critique quality: performance peaks at intermediate
reasoning length, while overly long
reasoning is accompanied by an overthinking penalty. The code is available at https://github.com/ZhongruChen/RPCBench.
Read the full abstract ▾
Artificial Intelligence
In-Context Neurofeedback: Can LLMs Control Their Internal Representations through Privileged Access?
Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi et al. (+2 more)
Whether large
language models (LLMs) can control their own internal representations matters for both machine metacognition and AI safety. A recent study applied neurofeedback to LLMs and claimed that they can control their internal representations. However, the reported control may rely on superficial mechanisms rather than genuine internal access because the control targets in that study are not privileged, meaning that a third party can infer them from the
prompt. We redesign the neurofeedback paradigm for LLMs so that the control target satisfies the privileged access requirement, which is closer to neurofeedback experiments in human cognitive neuroscience. Under this stricter setting, the models do not demonstrate reliable control over privileged internal representations, suggesting that previously reported control cannot exclude the possibility that it relies on superficial mechanisms. Our results indicate that rigorous assessments of metacognition in LLMs require evaluation methods that demand privileged access.
Read the full abstract ▾
All authors Koshiro Aoki, Ryota Takatsuki, Gouki Minegishi, Yusuke Haruki, Daisuke Kawahara
Artificial Intelligence · Cross-listed from cs.CV
Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segmentation for Waste Sorting
Udo Schlegel, Shubhangi, Gabriel Dax et al. (+3 more)
Obtaining labeled data for semantic
segmentation in applied settings (e.g., autonomous driving, industrial waste sorting) is expensive and often infeasible at scale. We present a cross-modal pseudo-labeling pipeline that enables unsupervised domain adaptation without any target-domain annotations. The pipeline is built on two core foundation models: SAM generates class-agnostic region proposals, and EVA-CLIP assigns semantic labels based on region-text similarity, with confidence filtering ensuring that only reliable pseudo-labels are used for self-training a
segmentation model. As an optional extension, BLIP provides
language-grounded verification for ambiguous regions, thereby improving pseudo-label quality without altering the overall pipeline. Evaluated on two domain shifts, synthetic-to-real autonomous driving and, with a primary focus, lab-to-factory industrial waste sorting, the pipeline consistently improves over source-only baselines. Our results demonstrate that pseudo-label quality, not quantity, is a decisive factor in self-training under domain shift, and that cross-modal
language grounding offers a practical path to reliable automatic annotation in deployment-critical applications.
Read the full abstract ▾
All authors Udo Schlegel, Shubhangi, Gabriel Dax, Sai Rahul Kaminwar, Florian Karl, Thomas Seidl
Artificial Intelligence
CARE: Contrastive Anchor-based Rubric Evolution for Large Language Model Post-Training
Siyuan Li, Xinxin Song, Chen Ruinian et al. (+5 more)
Rubric-based reinforcement learning decomposes open-ended instructions into
prompt-specific, flexible rubrics, making it better suited than reinforcement learning with verifiable rewards for post-training LLMs on open-ended tasks. However, static rubrics are inevitably hacked as the policy evolves, and existing dynamic approaches introduce new problems: undirected rubric extraction, unreliable hack detection, and unbounded rubric proliferation. We propose $\textbf{CARE}$ ($\textbf{C}$ontrastive $\textbf{A}$nchor-based $\textbf{R}$ubric $\textbf{E}$volution), which grounds every rubric
evolution step in a high-quality anchor response generated by a frontier model conditioned on the
prompt and its rubrics. At each training step, CARE contrasts the highest-scoring rollout against the anchor, enabling two complementary mechanisms: an Adaptive branch that reactively repairs reward misspecification; and a Chase branch that proactively converts frontier-level quality gaps into sharper rubrics. Together, the two branches $\textbf{maintain discriminative accuracy in the high-reward region}$—the precise region where reward over-optimization mostly originates. Experiments on WildChecklist-9K with Qwen2.5-7B-Base and Qwen2.5-7B-Instruct show that CARE achieves state-of-the-art performance on Arena-Hard-2.0, InfoBench, and FollowBench, and is the $\textbf{only}$ method whose win rate against GPT-4.1 anchor responses shows sustained improvement throughout 300 training steps; additional results on Llama-3.1-8B-Instruct and Qwen3-8B further indicate that CARE generalizes across model families.
Read the full abstract ▾
All authors Siyuan Li, Xinxin Song, Chen Ruinian, Jingjing Fan, Tingxiong Xiao, Yangen Hu, Ke Zeng, Jinli Suo
Artificial Intelligence
CacheBridge: Efficient Cross-Model KV Cache Transfer
Xingyu Qu, Siyuan Lu, Zhiyu Chen et al. (+2 more)
Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Recent closed-form cross-model KV transfer, hereafter Full-Head Mapping, avoids this replay by fitting a training-free affine mapper from source to target caches. However, its full-head design maps each target KV head from every source KV head in the selected layers, making transfer quality sensitive to architectural differences and causing mapper storage and application cost to grow with layer support. To this end, we introduce CacheBridge, which co-designs architecture-indexed mapper support,
attention-aligned calibration, and bounded mapper construction while retaining a closed-form affine interface for online deployment. CacheBridge restricts each target head to a matched source head, weights reconstruction errors by causal
attention sensitivity, and uses a fused GPU kernel to construct weighted sufficient statistics without materializing full observation tensors. Across three transfer directions, CacheBridge recovers the two Ministral 3 transfer directions where Full-Head Mapping loses substantial accuracy while preserving 99.83% mean target retention on Qwen3. On Qwen3 $14\mathrm{B}\to32\mathrm{B}$, it reduces mapper storage by $8\times$, accelerates application by up to $3.0\times$, matches \fullhead with one tenth of the calibration data, and reduces 500-sequence construction from 92.63 to 8.63 seconds ($10.7\times$).
Read the full abstract ▾
All authors Xingyu Qu, Siyuan Lu, Zhiyu Chen, Sheng Wang, Tao Lin
Artificial Intelligence
Denoising Diffusion Generative Models Secretly Calculate Attentions
Farzan Haddadi, Leila Monfared, Ebrahim Rezaii et al. (+3 more)
Denoising
diffusion models are the dominant architecture for image generation, whereas most natural
language generation and modeling are primarily handled by well-known
transformer architectures employing
attention mechanism. Here, we show that
diffusion models also inherently use an
attention mechanism very similar to that of
transformers. Therefore,
attention emerges as a universal machine learning principle, based on a general training objective. We also show similarities in basic functional principle of auto-encoders and
attention-based models. These equivalences allows us to interchange these designs based on practical requirements. As an example, we can reformulate the
diffusion framework to reduce the lengthy training process and computation-intensive image generation. Using this approach, a simplified
algorithm is proposed for image generation which is based on
attention mechanism. Results show that the
attention-based implementation achieves comparable performance with significantly less effort and computational resources.
Read the full abstract ▾
All authors Farzan Haddadi, Leila Monfared, Ebrahim Rezaii, Mohammadreza Malek-Mohammadi, Pejman Zakalvand, Narges Mokhtari
Artificial Intelligence
Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning
Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee et al. (+2 more)
Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing
multimodal approaches are limited by scarce annotated data and insufficient evaluation of
reasoning quality. This study proposes a two-stage training framework that integrates Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) within a unified data construction pipeline. From a single Human-in-the-Loop (HITL) annotation workflow, two complementary
datasets are derived, namely ReasoningSet, which contains validated rationales for SFT, and PreferenceSet, which comprises paired rationales for DPO-based
alignment. The framework evaluates both classification performance and explanation quality using automatic metrics, model-based scoring, and human ranking. Experimental results show that SFT improves accuracy from 73.64% to 78.29% and increases Macro-F1 by 29% compared to the baseline, while explanation quality improves by approximately 25%. Subsequent DPO
alignment further enhances interpretability on the PreferenceSet. Cross-model validation on InternVL-3-8B and LLaVA-1.5-7B demonstrates the robustness and generalizability of the approach. The proposed framework improves detection of underrepresented mild damage cases, reduces high-risk misclassifications, and strengthens
alignment between model
reasoning and human judgment. Overall, it provides a reproducible pathway to develop reliable
multimodal systems that deliver auditable, actionable disaster insights for emergency management.
Read the full abstract ▾
All authors Yuanjun Zhang, Fuzel Ahamed Shaik, Suvojit Acharjee, Fahad Khalid, Mourad Oussalah
Artificial Intelligence
FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study
Sai Puppala, Bhabani P. Sinha and Koushik Sinha
Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited from terrestrial
federated learning and ground-centric mission operations— ill-suited to satellites that differ by orders of magnitude in Size, Weight, Power, and Cost (SWAP-C), radiation tolerance, link availability, and propagation delay. We propose a heterogeneous
federated learning method based on the FractalNet architecture for orbital edge intelligence. We formalize contact-window-constrained, depth-heterogeneous
federated optimization and introduce a distributed path scheduler that assigns model depth as a function of SWAP-C constraints, predicted inter-satellite contacts, and training statistics. To reduce message overhead and energy consumption, each tier pools updates periodically rather than at every contact opportunity, and a three-tier agentic control plane governs in-space scheduling, anomaly escalation, and policy-governed autonomy. As a case study, we apply the framework to wildfire detection, where each orbital shell naturally learns a different semantic level of situational awareness: pixel-scale thermal anomalies at low Earth orbit (LEO), regional fire-front dynamics at medium Earth orbit (MEO), and larger-scale risk propagation at geostationary or high Earth orbit (GEO/HEO). Experiments on simulated mega-constellations validate the approach across convergence, communication efficiency, energy adaptation, scheduled-pooling savings, robustness, and latency.
Read the full abstract ▾
Artificial Intelligence
A Score Is Not a Policy: Measuring the Value of Adaptive Revision
Ayushi Chadha
As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller preserve the strategy guiding another process, and when should it revise it? We study this meta-level control problem in a hierarchical latent reasoner whose manager can retain or replace a commitment governing lower-level computation. Across three precommitted training seeds, learned revision timing produces qualitatively different policies, ranging from an almost deterministic early clock to substantially more state conditioned schedule distributions, yet none outperforms the best forced timing policy evaluated on the same frozen checkpoint. This separates state dependence from decision value: a controller can vary its actions with internal state without turning that variation into a reproducible task-performance benefit. A deeper intervention study on the original checkpoint shows that timing itself is consequential and order-sensitive, while exhaustive enumeration reveals that a strong fixed schedule captures most of the measurable value available from timing at this decision budget. Counterfactual PERSIST/REPLAN diagnostics further show why score-level evidence can be misleading when predictability is dominated by decision position rather than within-position discrimination. Together, these results argue that learned meta-level control should be evaluated along three separate axes: whether its score depends on state, whether that dependence changes realized behavior, and whether those changes capture outcome value beyond a strong non-adaptive policy.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generation
Yumi Lee, Harim Oh, Hyoryung Kim et al. (+52 more)
The rapid advancement of
vision-
language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pathology report generation remains limited by the scarcity of large-scale WSI–report
datasets and the complexity of mapping spatially distributed visual patterns to structured clinical text. To address this, we introduce a clinically curated Pan-Asia WSI–report
dataset of approximately 10,500 pairs from five institutions and establish the REG 2025
benchmark through a MICCAI challenge for systematic evaluation of
multimodal models. We analyze submitted methods spanning pretrained VLMs, multiple-instance learning frameworks, hierarchical expert models,
retrieval-augmented generation, and cross-modal
Transformers. Rather than indicating that VLM use alone was sufficient for superior performance, the results suggest that top-performing methods benefited from structured report representations, hierarchical diagnostic decomposition, and effective
multimodal grounding. We identify key limitations, including instability in quantitative attribute estimation (e.g., numeric
hallucination) and a tendency toward diagnostic overspecification, with some errors resembling known diagnostic pitfalls in routine pathology. These findings establish REG 2025 as a
benchmark for evaluating WSI-based structured report generation and
vision-
language understanding in computational pathology, providing insights for the design of clinically grounded
multimodal pathology models.
Read the full abstract ▾
All authors Yumi Lee, Harim Oh, Hyoryung Kim, Minji Kim, Eunsu Kim, Hyeseong Lee, Junya Fukuoka, Andrey Bychkov, Jijgee Munkhdelger, Rajiv Kumar Kaushal, Ayushi Sahay, Rajni Yadav, Bharathi Prabakaran, Sulen Sarioglu, Serdar Balc{\i}, Ilknur Turkmen, Yuri Tolkach, Christian Harder, Julian Westerdorf, Reinhard Buettner, Audun Ljone Henriksen, Sepp De Raedt, Byung Hyun Lee, Sungjin Lim, Joohoon Lee, Gwanghyun Kim, Se Young Chun, Suryakant Singh, Saarthak Kapse, Prateek Prasanna, Kyung A Kim, Yousun Kang, Sehwan Yoo, Sungman Hong, Shubham Innani, Michael Feldman, Spyridon Bakas, Ujjwal Baid, Prasad Dutande, Suhas Gajare, Bhakti Baheti, Serkan Sökmen, Ece Tuğba Cebeci, Ahmet Hal{\i}c{\i}, Musa Balc{\i}, Kardelen Peçenek, Srividhya Sainath, Kyongseok Jang, Messi H.J. Lee, Noorul Wahab, Bodong Du, Jiaming Zhang, Qixiang Zhang, Jang-Hwan Choi, Sangjeong Ahn
Artificial Intelligence
Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems
Yi Chen, Zikang Yu, Jiahai Wang et al. (+3 more)
Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced optimization solvers can effectively solve such problems. However, modeling complex VRP variants for solvers often requires substantial domain expertise, which limits the accessibility of advanced optimization technologies. In this paper, we propose Reinforcement Learning Enhanced LLMAgents(RLEA), a multi-
agent framework designed to automate the modeling of complex VRPs. RLEA introduces a lightweight neural Planner trained with Soft Q-learning to efficiently orchestrate the actions of LLM-based
agents. In addition, we equip the system with an evolutionary
memory module and
retrieval-augmented generation, enabling the
agent to leverage both accumulated experience and external solver knowledge during program generation and refinement for solving VRPs. We evaluated 48 distinct VRP variants across various solvers. The experimental results demonstrate that RLEA outperforms the previous state-of-the-ar method, achieving a 16.67% higher success rate while significantly reducing runtime errors. These results validate that integrating reinforcement learning with LLM-based
reasoning is highly effective for automated optimization modeling. The appendix is available at: https://doi.org/10.5281/zenodo.19134435.
Read the full abstract ▾
All authors Yi Chen, Zikang Yu, Jiahai Wang, Jinbiao Chen, Jianpeng Zhou, Zizhen Zhang
Artificial Intelligence
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline from Heterogeneous Humanitarian Sources
Ivan Decostanzi, Michele Ronco, Sergio Consoli et al. (+8 more)
Effective humanitarian response depends on the rapid synthesis of heterogeneous, high-volume information sources - a task that routinely exceeds human analytical capacity in the critical early hours of a crisis. We present a pipeline that combines structured disaster records from EM-DAT with unstructured documents from ReliefWeb and the European Media Monitor (EMM) to produce source-grounded disaster storylines and causal knowledge graphs supporting situational awareness for responders and analysts. Using
Retrieval-Augmented Generation, the pipeline extracts structured storylines - tabular event profiles covering 17 fields, from severity and key drivers to child-sensitive impact indicators - and constructs causal knowledge graphs where each node and edge is enriched with citation-grounded explanatory narratives, enabling full traceability back to primary sources. We evaluate the system on three diverse crisis use cases through a human evaluation involving 9 domain expert and 9 non-expert evaluators. Results confirm high
retrieval precision, strong faithfulness of extracted causal relations, and a clear expert preference for citation-grounded components over ungrounded alternatives. The pipeline is designed to scale to the full EM-DAT catalogue, with the goal of publicly releasing a new collection of disaster stories complementing the EM-DAT database.
Read the full abstract ▾
All authors Ivan Decostanzi, Michele Ronco, Sergio Consoli, Christina Corbane, Lorenzo Bertolini, Indaco Biazzo, Daria Mihaila, Manuel Garcia-Herranz, Felix Schwebel, Yelena Mejova, Kyriaki Kalimeri
Artificial Intelligence · Cross-listed from cs.SE
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided Code Repair
Anik Jha
Fault localization can focus a code model's repair on the statements a failing test implicates, but a targeted edit may succeed merely because it is small, and a second model call may succeed without using the failure at all. We separate these explanations with three arms applied to the same failed candidate: blind whole-solution resampling, spectrum-based localization followed by suspect-span infilling, and same-length infilling at a disjoint random code span. Across three frozen 26-32B models, three
benchmarks and 488 failing candidates, plus a separately declared 24B fourth model from a third family, three results follow. First, localization is rarely available: only 9.0% of failing candidates expose a failing public test with a usable spectrum. Second, among the 177 candidates localizable from a strong suite, localized infilling loses decisively to blind resampling at a matched attempt count (3:40, p = 3.0 x 10^-9), opposite to our hypothesis; the loss replicates in a third family at -11.3 points (95% CI [-16.6, -6.8]), and widening the edit does not rescue it. Third, against the random-span placebo localized infilling leads pooled (11:1, Holm-adjusted p = .019), but that lead resolves in no individual model under the analysis our shipped plan designates primary (best Holm p = .087), so we report the location effect as suggestive rather than established. Re-pricing attempts as
tokens narrows but does not overturn this: a span attempt spends 21.7 generated
tokens against 371.1, yet 16 localized attempts reach 6.8% while one blind attempt already reaches 10.1%. Infilling reproduces the removed span verbatim in 48.9% of attempts, which is why more budget does not help. We restrict every localization conclusion to the 24-32B models tested.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
Tongtong Wang, Mingzhu Xu, Chenglong Yu et al. (+3 more)
InfRared Small Target Detection (IRSTD) is a challenging task. Relying solely on pixel-level information,
vision-only methods struggle to distinguish targets from clutter. Current
multimodal methods typically describe both targets and backgrounds with a single textual
prompt. Such an approach lacks dedicated regional guidance and ignores infrared semantic asymmetry. Consequently, it provides insufficient background suppression information and introduces severe feature optimization conflicts, overwhelming small targets with noise. To address these issues, we propose a novel Asymmetric Dual-text Guided Network (ADGNet). Specifically, accounting for the infrared semantic asymmetry, we first design the Asymmetric Dual-text
Prompt (ADP), comprising an image-agnostic abstract target
prompt and an image-specific detailed background
prompt. To leverage these
prompts, we introduce an Asymmetric Dual-Branch Interaction (ADBI) module to separately guide visual features with their respective text priors, protecting targets from noise while suppressing background clutter. Subsequently, we introduce an Adaptive Feature Aggregation (AFA) module to dynamically fuse features from the two branches. Furthermore, we construct a
multimodal Asymmetric Image-Text Infrared (AITIR)
dataset by providing asymmetric text annotations for three public
datasets (IRSTD-1K, NUDT-SIRST, and SIRST). Extensive experiments demonstrate that ADGNet outperforms 21 state-of-the-art (SOTA) methods. Code is available at https://github.com/iLearn-Lab/MM26-ADGNet.
Read the full abstract ▾
All authors Tongtong Wang, Mingzhu Xu, Chenglong Yu, Jing Wang, Xiaohui Lin, Weili Guan
Artificial Intelligence · Cross-listed from physics.ao-ph
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System Modeling
Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño et al. (+5 more)
As machine learning and artificial intelligence find their way into nearly every aspect of
climate, weather, and Earth system modeling, it is worth pausing to consider what our design decisions imply for the science and for the computational resources we consume. A growing body of literature addresses the ethical and sustainable development of ML/AI, yet translating these principles into day-to-day research practice remains a challenge as most of best practices are dispersed across multiple studies and commentaries. Here, we distill these discussions into a practical checklist that ML/AI and Earth system science practitioners can use to assess and reduce the environmental footprint of their own applications, organised around the successive stages of the model development pipeline. We complement the checklist with a selection of metrics drawn from the literature for estimating the energy consumption and carbon footprint of a project. For each question, we point to concrete examples and actionable suggestions from recent literature, aiming to bridge the gap between aspirational principles and the decisions researchers face at every stage of the development cycle.
Read the full abstract ▾
All authors Filippo Dainelli, Amirpasha Mozaffari, Marina Castaño, Aina Gaya i Àvila, Lluís Palma Garcia, Alessio Melli, Oscar Dimdore Miles, Amanda Duarte
Artificial Intelligence
Towards Generalizable Visually Grounded Exploration of Household Devices
Linhao Zheng, Zeming Liu, Wangke Chen et al. (+4 more)
Recent advancements in
Vision-
Language Models (VLMs) have demonstrated impressive capabilities in static visual recognition and high-level semantic
reasoning. However, current
embodied exploration paradigms still heavily rely on imitation learning from human-annotated trajectories, which severely limits
agents' generalization ability. The key bottleneck of realizing general autonomous
embodied agents lies in Generalizable Visually Grounded Exploration: the ability to operate novel devices without manuals or specific training by actively grounding abstract world knowledge into fine-grained visual affordances. Yet, existing
benchmarks fail to evaluate this capability: they generally rely on explicit documents and annotated trajectories, neglecting the dynamic Hypothesis-Interaction-Refinement process essential for functional device operation. To bridge this gap, we introduce VGEBench, a comprehensive
benchmark designed to evaluate the generalizable visually grounded exploration capabilities of VLMs. Unlike static
datasets, we construct a Logic-Driven State Machine framework. This framework simulates multi-turn interaction loops, compelling
agents to achieve goals by active visual perception and feedback-driven correction. Experimental results demonstrate that existing VLMs face significant challenges in translating semantic knowledge into physical execution and maintaining long-horizon state tracking.
Read the full abstract ▾
All authors Linhao Zheng, Zeming Liu, Wangke Chen, Li Zeng, Wanxiang Che, Heyan Huang, Yuhang Guo
Artificial Intelligence · Cross-listed from cs.SE
Probabilistic Model Checking of Autoregressive Neural Sequence Models
Helge Spieker, Dennis Gross and Arnaud Gotlieb
Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under test (SUT) places on constraint-violating alternatives that are reachable under sampling and what fraction of the input population satisfies a domain requirement. We answer both with probabilistic model checking. The pipeline extracts a discrete-time Markov chain (DTMC) from the SUT's
token-by-
token generation, verifies formal PCTL specifications with the PRISM model checker, and aggregates the per-input verdicts into a coverage curve over the input space. A soundness
theorem establishes the DTMC as an under-approximation, so every verdict yields a certified interval on the SUT's true reachability probability. The coverage built from those verdicts is, therefore, conservative by construction. A counterexample-guided abstraction refinement (CEGAR) loop adaptively tightens the interval, and a maximum-likelihood
algorithm extracts the most probable falsifying trace. Two case studies exercise the pipeline. On a GPT-2 computer-aided process-planning (CAPP) model with 100% test accuracy, the pipeline quantifies the probability mass greedy decoding hides, but that is reachable with sampling; and identifies the smallest training fraction at which an ordering requirement holds population-wide, neither of which test accuracy can report. We then verify the SMILES molecular generator with a 50x larger vocabulary. The only change is an external chemical-validity oracle, and the pipeline identifies the gap between structural completeness and chemical validity.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Replacing Training with Memory: Listwise Selection for Text-to-SQL
Yeonseok Jeong, Soyoung Yoon, Seongjun Lee et al. (+1 more)
Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise selection, by jointly comparing multiple candidates, has been widely adopted, but fine-tuning listwise selectors is costly. We thus propose a fine-tuning-free listwise selector. We replace two major fine-tuning objectives with inference-time strategies: (1) learning selection criteria as ordering and (2) mitigating positional bias. First, we build reusable structured
memories instead of learning selection behavior as model parameters. Given a question, MaP-SQL retrieves
memories distilled from training data that encode how natural
language maps to schema elements, SQL operations, and expected outputs. These
memories serve as explicit decision criteria for evaluating candidates in a listwise manner. Second, to mitigate ordering bias of listwise selectors, we aggregate rankings across multiple input permutations, with inference cost optimized by execution results and pointwise scoring. Our approach improves selection accuracy while maintaining efficiency and compatibility with existing large
language models. Across Text-to-SQL
benchmarks, it produces more stable selection without fine-tuning and fewer unnecessary comparisons than existing methods. On BIRD-dev, it outperforms the previous state-of-the-art selector-based method R^3-SQL by 2.02 execution accuracy points on average using the same candidate sets, with 2.92x fewer
tokens.
Read the full abstract ▾
All authors Yeonseok Jeong, Soyoung Yoon, Seongjun Lee, Seung-won Hwang
Artificial Intelligence
FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation
Kewei Li, Rongying Zhang, Xueli Wang et al. (+6 more)
Token aggregation converts
token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original
token space. We introduce Frequency-Domain Latent-
attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the
Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral
tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated
token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based
language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven
language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-
attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across
protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.
Read the full abstract ▾
All authors Kewei Li, Rongying Zhang, Xueli Wang, Xiwen Gong, Zhongjian Wang, Qiuchen Zhao, Lan Huang, Ruochi Zhang, Fengfeng Zhou
Artificial Intelligence · Cross-listed from cs.CV
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
Xurui Song, Weishi Wang, Zhongqi Yue et al. (+5 more)
Whether
attention weights faithfully reflect model
reasoning has been actively debated in NLP, yet this question remains largely unexplored for the visual modality in
Vision-
Language Models (VLMs). We address this gap through causal perturbation analysis on current VLMs, evaluating both the comprehensiveness and sufficiency gap of
attention-ranked visual
tokens. Our analysis reveals that visual
attention faithfulness is heterogeneous, manifesting in three distinct processing modes: Faithful-Sufficient, where top-$k$
attention tokens are both necessary and sufficient for prediction; Faithful-Distributed, where they are necessary but broader visual context remains required; and Non-Focal, where no localized
attention region is individually necessary while visual information remains an essential trigger for prediction. Furthermore, human-annotated ground-truth regions satisfy comprehensiveness in only $\sim 60$% of cases compared with model
attention rankings, revealing systematic divergence between model visual reliance and human intuition. We demonstrate these patterns across both general VQA on VQAv2 and document tasks on VRDU and ChartQA, showing that visual
attention faithfulness varies systematically with processing demands and model architectures rather than being uniformly faithful or unfaithful.
Read the full abstract ▾
All authors Xurui Song, Weishi Wang, Zhongqi Yue, Kuluhan Binici, Tao Bai, Hongxin Shao, Daniel Dahlmeier, Jun Luo
Artificial Intelligence · Cross-listed from cs.LG
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian et al. (+6 more)
Self-evolving
agents advance toward autonomy by optimizing their harness—
prompts, skills, tools, and execution logic—based on environmental feedback. This paradigm, however, is hampered by three challenges: credit assignment failure, where terminal success/failure feedback makes it ambiguous which step caused the error; shortcut learning, where
agents memorize task-specific patterns rather than acquire generalizable capabilities; and catastrophic forgetting, where unguarded updates degrade previously acquired competence. In this paper, we introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable
agent self-
evolution. HarnessEvolve decouples the execution
agent from the evolutionary pipeline, assigning execution, evaluation, optimization, and gating to independent
agent modules, enabling generalizable and stable harness improvements. Specifically, HarnessEvolve overcomes credit assignment failure by generating reference trajectories (execution paths produced when given the ground-truth answers) and aligning failed executions against them to extract error signals, which are clustered to reveal systematic failure patterns. To prevent shortcut learning and catastrophic forgetting, candidate harness updates must pass two gates: a quality gate that filters data leakage and
prompt bloat, and a performance gate that accepts each update if it improves on the current batch without degrading recent batches, with epoch-end validation on a held-out set selecting the best-performing accepted
agent snapshot. We conduct extensive experiments on several
benchmarks spanning open-domain and enterprise scenarios, using different models and
agent frameworks. Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all
benchmarks and settings, confirming reliability across task domains.
Read the full abstract ▾
All authors Wen Jiang, Mingmin Chu, Yimeng Tian, Qianxin Zhang, Haofei Yang, Rui Yang, Yang Liu, Tao Lv, Fangming Li
Artificial Intelligence
Polished but Unresolved: Identifying Late-Stage Pressure States in Long-Horizon Tool-Use Agents
Haoyang Chen, Yi Liu, Jianzhi Shao et al. (+3 more)
Long-horizon tool-use
agents need not only to search and plan, but also to decide when to finalize. We study late-stage pressure states, in which an
agent is biased toward submitting a final answer that appears complete and polished while key constraints remain unresolved. We first train a linear probe to show that this pressure state is identifiable from the
agent's hidden states. Then, we use activation interventions along this pressure direction and find that shifting the hidden states changes both the pressure score and whether the
agent continues tool use or submits early. Through controlled context manipulations, we further see that the pressure is mitigated by constraint clarity and action mapping. Based on these findings, we propose Probe-Sensed Pressure Relief (PSPR), a plugin that applies lightweight pressure relief direction under moderate pressure and moves to structured organization under high pressure risk. Experiments on multiple long-horizon
benchmarks show that our method consistently strengthens existing
agent methods.
Read the full abstract ▾
All authors Haoyang Chen, Yi Liu, Jianzhi Shao, Xiaozhou Xu, Zhe Sun, Wei Hu
Artificial Intelligence
AnalysisBank: An Expert Analysis Pattern Library for Financial Report Generation
Yajing Yang, Yunshan Ma, Kelvin J.L. Koa et al. (+1 more)
We argue that financial report generation should operate at the analytical rather than structural level, composing content from data-derived insights rather than high-level topics or sections. To this end, we propose AnalysisBank, which distills expert reports into a reusable library of Analyses, each pairing a data signal, an analytical move, and the expert span it was derived from. At inference time, AnalysisBank matches input signals to library entries and applies the retrieved moves to compose the report. A study of Analyses distilled from 550 expert reports reveals a heavy-tailed distribution of 47-52 signal types spanning 13 move types. On two financial
benchmarks across four LLM backbones, AnalysisBank increases the proportion of novel, data-grounded insights by 1.7-3.7x over structural-level baselines. Transfer to scientific writing suggests that the distinction generalizes beyond finance. Code and the distilled Analysis library are available at https://github.com/yajingyang/AnalysisBank.
Read the full abstract ▾
All authors Yajing Yang, Yunshan Ma, Kelvin J.L. Koa, Min-Yen Kan
Artificial Intelligence
One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning
Xiaowei Sun, Jin Li, Yili Hong et al. (+2 more)
While reinforcement learning has enabled LLM-based search
agents to invoke external tools, existing methods train under fixed budgets and cannot adapt when constraints vary at deployment. We propose AnySearch, a framework that enables a single policy to perform budget-aware search under any budget constraint through a training scaffold and curriculum reinforcement learning. In the first phase, we train the
agent with explicit budget state injection and structured
reasoning prompts that guide efficient allocation under linearly decaying budgets. In the second phase, the scaffold is removed and the
agent learns to operate autonomously under adaptively sampled budget constraints, matching inference conditions. Both phases are optimized with a composite reward that couples answer accuracy with budget efficiency through absolute and relative signals, where an adaptive weight amplifies the efficiency signal for high-accuracy queries and attenuates it for low-accuracy ones. Extensive experiments on seven general and multi-hop QA
benchmarks show that our method outperforms baselines across all budget scales, generalizes to unseen constraints beyond the training range, and achieves superior tool productivity without excessive
token overhead. Our code is available at https://github.com/xwsun01/AnySearch.
Read the full abstract ▾
All authors Xiaowei Sun, Jin Li, Yili Hong, Yikun Fu, Yanghua Xiao
Artificial Intelligence · Cross-listed from cs.HC
Ctrl-F-Resist. Practices, Challenges, and Technical Needs of Civil Society Organizations Monitoring the Far-Right Online
Elisabeth Steffen and Helena Mihaljević
As far-right actors increasingly exploit online platforms to disseminate ideology and mobilize supporters, civil society organizations (CSOs) play a vital yet underrecognized role in monitoring antidemocratic dynamics online. Unlike fact-checkers or content moderators, CSOs engage in long-term, contextualized analysis, often in resource-constrained settings and under precarious conditions. Despite their critical societal role, CSOs face significant barriers to adopting or co-developing technical solutions, including legal uncertainty, limited platform access, and chronic underfunding. Existing research and tool development efforts have largely overlooked these actors in favor of more institutionally embedded stakeholders. This paper addresses this gap through a qualitative study with 15 practitioners from 12 Germany-based CSOs engaged in online monitoring, positioning them as key yet overlooked stakeholders in the governance of digital spaces. We explore their current practices, challenges, and expectations regarding technological support. Our findings show that monitoring remains largely manual due to the lack of tailored tools, with enhanced search capabilities emerging as the most pressing technical need. While participants express openness to AI-supported features such as media processing and content discovery, many remain skeptical of automated classification, citing concerns around trust, legal usability, and professional credibility. Grounded in these findings, we introduce a conceptual monitoring workflow and describe its implementation in an open-source Telegram monitoring prototype designed to flexibly support diverse monitoring goals. We outline concrete design, policy, and research recommendatios, and introduce the manual labor trap as an empirically grounded concept that explains why monitoring CSOs tend to remain locked into labor-intensive, low-capacity arrangements.
Read the full abstract ▾
Artificial Intelligence
Towards a Reliable and Practical Eval Pipeline
Emma Thuong Nguyen and Abhishek Ghose
LLM-based software systems increasingly require effective "evals" as quality gates in the development lifecycle. However, existing work typically addresses individual aspects of eval reliability rather than the full set of practical requirements. We present an end-to-end eval pipeline that combines eval checklist creation, with learned aggregation for checklist responses, to improve agreement across LLM judges and accuracy against human judgments. The framework additionally pro- vides self-consistency, explanations, and prediction uncertainty, and we empirically demonstrate its effectiveness.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cond-mat.mtrl-sci
Agentic programs: an emerging form of scientific software in computational materials science
Yunsung Lim, Haekwan Jeon, Jaesun Kim et al. (+2 more)
Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that recent LLM-based
agent harnesses enable an emerging form of scientific software, agentic programs, that combine deterministic
algorithms with bounded LLM-based judgment, task-specific verification, episodic maturation, and complete delegation in production. We illustrate this concept with DeMARS, an agentic program for constructing atomistic models from experimentally measured disordered
crystal structures.
Read the full abstract ▾
All authors Yunsung Lim, Haekwan Jeon, Jaesun Kim, Jisu Kim, Seungwu Han
Artificial Intelligence · Cross-listed from cs.SD
MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries
Utsab Ghosh and Roshni Chakraborty
Dominant audio classification pipelines rely either on compact handcrafted summaries or on fixed time-frequency frontends such as log-mel representations prior to deep modeling. While highly successful, these representations do not explicitly expose the physical dynamics of the underlying sound-generating event. We introduce MADS (Multi-view Acoustic Descriptor Set), a compact 19-dimensional physics-informed descriptor set de- signed to capture complementary spectral, temporal, mechanical, and
stochastic structure in audio signals. Rather than treating sound only as a spectral pattern, MADS encodes properties related to excitation, damping, periodicity, impulsiveness, and structural consistency within a unified multi-view representation. We evaluate MADS using standard classical machine learning models on ESC-10, ESC-50, and MSoS, and compare it against two conventional handcrafted baselines: a compact 26D MFCC- based baseline and an expanded 38D spectral-summary baseline. Across ESC-10 and ESC-50, MADS achieves the strongest peak results overall, reaching 81.00% and 52.78%, respectively, while using roughly half the dimensionality of the 38D baseline. On MSoS, MADS again delivers the strongest top-end performance, reaching 67.48%. These results establish MADS not merely as a competitive standalone descriptor set, but as the foundational descriptor layer of a broader acoustically grounded representation program for future frame-level and deep-learning-compatible audio modeling.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Instella-MoE Technical Report
Jiang Liu, Sudhanshu Ranjan, Prakamya Mishra et al. (+10 more)
In this work, we introduce Instella-MoE, a fully open Mixture-of-Experts (MoE)
language model with 16 billion total parameters and 2.8 billion active parameters per
token, trained entirely from scratch on AMD Instinct MI300X and MI325X GPUs. Instella-MoE combines a sparsely activated MoE design with architectural and system-level innovations, including Gated Multi-head Latent
Attention (Gated MLA) and FarSkip-Collective connectivity, enabling efficient large-scale training and inference. The model is developed through a multi-stage pipeline comprising pre-training, mid-training, long-context extension, supervised fine-tuning with feedback-driven data curation, direct preference optimization, and reinforcement learning with Multi-Teacher On-Policy
Distillation. Instella-MoE achieves an average score of 76.7 across standard pre-training
benchmarks, outperforming prior fully open models including OLMo-3-7B, SmolLM3-3B, and OLMoE-1B-7B, while remaining competitive with open-weight MoE and dense baselines at comparable active-parameter scales, including Moonlight-16B-A3B and Qwen3.5-4B. After post-training, our final Think checkpoint achieves an average score of 73.2 across instruction-following,
reasoning, math, coding, and chat
benchmarks, outperforming both fully open and open-weight models with comparable or larger active parameter counts in our evaluation. To support transparent and reproducible research, we release the complete Instella-MoE model flow, including model weights, training configurations, data mixtures, and training code. Together, these contributions establish Instella-MoE a strong, fully open foundation for efficient, high-performing MoE models and reproducible research.
Read the full abstract ▾
All authors Jiang Liu, Sudhanshu Ranjan, Prakamya Mishra, Yonatan Dukler, Gowtham Ramesh, Jialian Wu, Ximeng Sun, Wen Xie, Chaojun Hou, Vikram Appia, Zhenyu Gu, Zicheng Liu, Emad Barsoum