Artificial Intelligence
To Eun Kim, Xuhong He, Dishank Jain et al. (+3 more)
Decentralized deployment of LLM
agents with diverse capabilities motivates infrastructure for knowledge sharing across heterogeneous
agent populations. Just as search engines index human-generated artifacts for human problem solving,
retrieval systems can organize
agent-generated artifacts for reuse across
agents, extending
retrieval-augmented generation from human-authored documents to
agent-generated ones.
Agent trajectories in particular encode reusable procedural knowledge, yet are typically discarded after a single use or retained only by the producing
agent, forcing newly instantiated
agents to rediscover existing solutions. We propose Multi-
Agent Transactive
Memory (MATM), a framework for population-level storage and
retrieval of
agent trajectories, where producer
agents contribute trajectories to a shared repository and consumer
agents retrieve them to improve task execution. In interactive environments with long, procedurally rich trajectories (ALFWorld and WebArena), retrieving from MATM improves downstream task performance and reduces interaction steps without coordination or joint training, positioning MATM as a design pattern for population-level experience sharing in open
agent ecosystems.
Read the full abstract ▾
All authors To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz
Artificial Intelligence · Cross-listed from cs.CY
Measuring Biological Capabilities and Risks of AI Agents
Patricia Paskov, Jeffrey Lee, Kyle Brady et al. (+1 more)
This paper addresses a rapidly emerging policy challenge: how to generate and interpret credible evidence about the biological capabilities and risks of AI scientists, or agentic AI systems capable of autonomously or collaboratively performing multi-step scientific tasks. As these systems enter real research workflows, decision-makers increasingly face evaluation results whose meaning depends on underlying design choices that are often implicit or under-documented. We synthesize current evidence on AI-enabled biological risks and introduce biological agentic evaluations as a promising, but interpretation-sensitive, tool for assessing these systems. Our central contribution is a set of practical, experience-grounded considerations – drawing from our own evaluations – that show how choices around defining, designing, running, scoring, and documenting evaluations materially shape what results do and do not imply about risk. The analysis is intended to help policymakers interpret biological evaluation outputs with appropriate caution; guide public and private funders toward high-leverage investments in AI-biology evaluation research; and support biosecurity practitioners assessing emerging AI systems. A secondary audience includes researchers designing or conducting agentic evaluations within frontier AI labs, AI providers, scientific institutions, and third-party evaluation organizations.
Read the full abstract ▾
All authors Patricia Paskov, Jeffrey Lee, Kyle Brady, Alyssa Worland
Artificial Intelligence
MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments
Wei Yu, Suxing Liu, Minjie Yu et al. (+4 more)
Deep research
agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-
retrieval-only task designs, and the inefficiency of outcome-based reinforcement learning. In this work, we propose MetaResearcher, a novel framework that scales deep research
agent training across four synergistic dimensions. First, we introduce an Evolving Virtual World that injects temporal dynamics and
adversarial misinformation into the training environment, forcing
agents to develop source credibility assessment and temporal conflict resolution skills. Second, we design Discovery-Oriented Tasks – including hypothesis generation and contradiction resolution – that transcend simple fact
retrieval and push
agents toward genuine research behaviors. Third, we propose a Self-Reflective Meta-Reward mechanism within the GRPO framework that jointly optimizes for answer correctness, search path efficiency, reflection depth, and tool call diversity, directly addressing the repetitive action loop problem observed in prior work. Fourth, we introduce a Heterogeneous Multi-
Agent Swarm architecture comprising specialized Scout, Filter, and Synthesizer models that learn collaborative research strategies through coordinated reinforcement learning. Built upon the LiteResearcher infrastructure, MetaResearcher requires zero marginal API cost for training while targeting substantial improvements in both
benchmark performance (
GAIA, Xbench-DS) and epistemic robustness under
adversarial conditions. We present the complete framework design, training methodology, and planned experimental validation.
Read the full abstract ▾
All authors Wei Yu, Suxing Liu, Minjie Yu, Jiahao Wang, Zhijian Zheng, Haocheng Deng, Bing Li
Artificial Intelligence · Cross-listed from cs.LG
SL-S4Wave: Self-Supervised Learning of Physiological Waveforms with Structured State Space Models
Feng Wu, Harsh Deep, Eric Lehman et al. (+5 more)
Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal complexity, inherent noise, and limited labeled data. While recent self-supervised learning (SSL) methods, based on various encoder architectures such as convolutional neural networks, have been proposed to learn representations from unlabeled data, they often fall short in capturing long-range dependencies and noise-invariant features. Structured state space models (S4) excel at long-sequence modeling, but existing S4 architectures fail to capture the unique characteristics of multichannel physiological waveforms. In this work, we propose SL-S4Wave, a self-supervised learning framework that combines contrastive learning with a tailored encoder built on structured state space models. The encoder incorporates multi-layer global convolution using multiscale subkernels, enabling the capture of both fine-grained local patterns and long-range temporal dependencies in noisy, high-resolution multichannel waveforms. Extensive experiments on real-world
datasets demonstrate that SL-S4Wave (1) consistently outperforms state-of-the-art supervised and self-supervised baselines in a challenging arrhythmia detection task, (2) achieves high performance with significantly fewer labeled examples, showcasing strong label efficiency, and (3) maintains robust performance on long waveform segments, highlighting its capacity to model complex temporal dynamics in long sequences that most existing approaches fail to efficiently model, and (4) transfers effectively to unseen arrhythmia types, underscoring its robust cross-domain generalization. We additionally evaluate SL-S4Wave on multiple
EEG tasks, achieving superior performance over strong baselines, demonstrating generalizability of our approach beyond cardiac waveforms.
Read the full abstract ▾
All authors Feng Wu, Harsh Deep, Eric Lehman, Sanyam Kapoor, Guoshuai Zhao, Rahul G. Krishnan, Gari Clifford, Li-wei H Lehman
Artificial Intelligence · Cross-listed from cs.CR
FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming
Daeyoung Park, Chaeyun Kim, Junghwan Kim et al. (+4 more)
Existing safety
benchmarks target general
adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation. We introduce FinRED, an expert-guided red-teaming framework for financial LLM safety evaluation developed with financial experts. FinRED uses a novel two-level taxonomy mapping global standards (e.g., FATF and EU DORA) to threats ranging from regulatory evasion to complex fraud, integrated with a scalable pipeline that converts real financial documents into context-rich red-teaming Behavioral
Prompts (seeds) through an expert-defined schema. Rigorous expert validation confirms seed plausibility and realism for meaningful LLM safety evaluation. We also provide an expert-validated, finance-specific rubric that goes beyond disclaimer checks, aligns more closely with human experts than static one-size-fits-all rubrics, and reduces critical false negatives from 28 to 12. Aligned with internationally adopted risk-management and information-security standards (e.g., ISO/IEC 27001), FinRED is deployed in South Korea's Financial Security Institute (FSI) regulatory sandbox for generative AI security evaluation in real financial services. To mitigate dual-use risks, the
dataset, generation pipeline,
prompt template, and evaluation framework are gated for qualified researchers at https://github.com/selectstar-ai/FinRED-paper and https://huggingface.co/
datasets/datumo/FinRED.
Read the full abstract ▾
All authors Daeyoung Park, Chaeyun Kim, Junghwan Kim, Jinyoung Jeong, Eunji Song, Yongtaek Lim, Minwoo Kim
Artificial Intelligence
A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models
Jiayi Wang and Xu-Yao Zhang
Although large
language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain
hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs. In practice, many mainstream LLMs are only accessible through restricted APIs, where internal signals such as logits and hidden states are unavailable, making black-box UE especially important. However, existing work on black-box UE for LLMs remains fragmented in methodology and lacks a unified empirical comparison. To address this gap, we present a systematic review of black-box UE methods and organize them into five categories: verbalization-based, sampling-based, explanation-based, multi-
agent, and hybrid methods. We further build a unified evaluation framework and
benchmark 24 representative methods across 4 models and 4
dataset settings. Our results show that no single method consistently dominates across all settings. Nevertheless, methods that reason over and compare candidates in the answer space are generally effective, and hybrid methods that combine multiple uncertainty signals perform well under most conditions. By releasing the
benchmark data and a unified evaluation framework, we aim to facilitate reproducible comparisons and support future research, while our empirical findings provide practical guidance for developing future black-box UE methods for LLMs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
PSCT-Net: Geometry-Aware Pediatric Skull CT Reconstruction via Differentiable Back-Projection and Attention-Guided Refinement
Dong Yeong Kim, Jaewon Choi, Youmin Shin et al. (+5 more)
Computed
Tomography (CT) is essential for diagnosing pediatric craniofacial abnormalities, yet poses radiation risks to developing anatomies. Reconstructing 3D CT from sparse bi-planar X-rays offers a low-dose alternative but is severely ill-posed. Existing methods employ geometry-agnostic feature lifting, naively projecting 2D features into 3D without explicit spatial modeling, causing depth ambiguity and degraded osseous boundaries. We present PSCT-Net, a geometry-aware framework with differentiable back-projection. Differentiable back-projection establishes a spatially faithful volumetric prior, alleviating depth ambiguity. An
Attention-Guided Projection (AGP-3D) module then learns non-linear voxel-wise correspondences between 2D regions and 3D locations. A Bidirectional Mamba (BiM-3D) module captures long-range volumetric dependencies with linear complexity. We further curate a private institutional pediatric skull CT cohort, PedSkull-CT, comprising normal and pathological cases for internal evaluation, addressing the gap in adult-centric, trunk-focused
datasets. Project page and code are available at https://dydevelop.github.io/PSCT-Net/.
Read the full abstract ▾
All authors Dong Yeong Kim, Jaewon Choi, Youmin Shin, JunGyu Lee, Myeongseop Kim, Jinwook Choi, Joo Whan Kim, Young-Gon Kim
Artificial Intelligence · Cross-listed from cs.CL
Large Language Models Do Not Always Need Readable Language
Jiayi Zhu, Haoxuan Peng, Junxi Wang et al. (+3 more)
Large
language models (LLMs) are commonly prompted and interfaced with human-readable natural
language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual forms that sacrifice human readability while remaining recoverable by LLMs. We refer to this class of model-centric textual representations as BabelTele, approached here not as a fixed protocol but as an empirical probe into LLMs' capacity to generate and interpret such representations. Through readability diagnostics, model likelihood measures, human questionnaires, and downstream task evaluations, we find that BabelTele can substantially depart from ordinary natural
language while preserving core semantics for instruction-tuned LLMs. As a task-agnostic representational paradigm, BabelTele demonstrates high information density, maintaining 99.5% semantic fidelity even when the text volume is condensed to 27.9% of its original length. We further evaluate its semantic robustness in cross-model transfer,
agent memory, and multi-
agent communication. Results suggest that BabelTele can reduce context overhead while generally maintaining reliable downstream performance, although its effectiveness depends on the compressor-reader pair and task setting. These findings indicate that human readability, natural-
language typicality, and model-side semantic recoverability can be partially decoupled, opening a path toward model-native representations in future exploration of LLM systems.
Read the full abstract ▾
All authors Jiayi Zhu, Haoxuan Peng, Junxi Wang, Liang Ke, Chen Zhang, Linfeng Zhang
Artificial Intelligence · Cross-listed from cs.LG
Neural Additive and Basis Models with Feature Selection and Interactions
Yasutoshi Kishimoto, Kota Yamanishi, Takuya Matsuda et al. (+1 more)
Deep neural networks (DNNs) exhibit attractive performance in various fields but often suffer from low interpretability. The neural additive model (NAM) and its variant called the neural basis model (NBM) use neural networks (NNs) as nonlinear shape functions in generalized additive models (GAMs). Both models are highly interpretable and exhibit good performance and flexibility for NN training. NAM and NBM can provide and visualize the contribution of each feature to the prediction owing to GAM-based architectures. However, when using two-input NNs to consider feature interactions or when applying them to high-dimensional
datasets, training NAM and NBM becomes intractable due to the increase in the computational resources required. This paper proposes incorporating the feature selection mechanism into NAM and NBM to resolve computational bottlenecks. We introduce the feature selection layer in both models and update the selection weights during training. Our method is simple and can reduce computational costs and model sizes compared to vanilla NAM and NBM. In addition, it enables us to use two-input NNs even in high-dimensional
datasets and capture feature interactions. We demonstrate that the proposed models are computationally efficient compared to vanilla NAM and NBM, and they exhibit better or comparable performance with state-of-the-art GAMs.
Read the full abstract ▾
All authors Yasutoshi Kishimoto, Kota Yamanishi, Takuya Matsuda, Shinichi Shirakawa
Artificial Intelligence · Cross-listed from cs.LG
When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning
Daehwan Kim, Haejun Chung and Ikbeom Jang
Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global
quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular
datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without
dataset-specific discretization tuning. We further introduce a medical tabular SSL
benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
CSWinUNETR: Segmentation of Thin Anatomical Structures in Medical Images
Junho Moon, Haejun Chung and Ikbeom Jang
Accurate
segmentation of thin, tortuous anatomical structures, such as retinal vessels, cerebral vasculature, and facial wrinkles, remains challenging due to low contrast, frequent discontinuities, and severe class imbalance. Although recent convolutional and
Transformer-based models have improved performance, they often yield fragmented predictions and fail to recover fine branches. We propose CSWinUNETR, a general-purpose backbone for 2D and 3D thin-structure
segmentation. It employs cross-shaped stripe self-
attention to model long-range principal-axis context and incorporates cyclic shifts to enhance information exchange across stripes. To better preserve fine-grained details, we further introduce a detail-enhanced multi-scale self-
attention module that aggregates contextual features from multi-resolution representations. In addition, we propose sparse-control dynamic snake convolution, which reconstructs reliable dense curvilinear kernels from sparsely predicted control points to better follow tortuous geometry. Extensive experiments on four
benchmarks across ophthalmology, neurovascular imaging, and dermatology demonstrate that CSWinUNETR consistently outperforms state-of-the-art methods without task-specific post-processing or
topology-aware losses. The code is available at https://github.com/labhai/CSWinUNETR.
Read the full abstract ▾
Artificial Intelligence
TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability
Geon Kim, Dara Ron, Sukhdeep Singh et al. (+5 more)
Key Performance Measurement (KPM)
forecasting is essential for proactive network management of 5G and next-generation telecom networks. However, existing machine learning (ML) approaches face significant limitations in scalability and explainability, restricting their effectiveness in real-world deployments. We propose TelcoAgent, a foundation model-based framework that enables accurate, scalable, and explainable
forecasting of multiple KPMs across diverse network
cells without the need for site-specific training. Specifically, the framework comprises three key components: (i) an automated three-
agent pipeline that constructs a 3rd Generation Partnership Project (3GPP) knowledge graph directly from specification documents, (ii) a scalable, time-series foundation model (TSFM)-based prediction pipeline to deliver accurate, zero-shot
forecasting, and finally (iii) a
reasoning and explanation pipeline that provides actionable, domain-grounded diagnostics. Evaluated using a 3-month, real-world, city-scale 5G KPM
dataset from a U.S.-based network operator, TelcoAgent demonstrates high
forecasting accuracy for all 7 considered KPMs per
cell across 200
cells, while delivering explainable insights and actionable instructions to address network degradations.
Read the full abstract ▾
All authors Geon Kim, Dara Ron, Sukhdeep Singh, Suyog Moogi, Pranshav Gajjar, V V N K Someswara Rao Koduri, Een Kee Hong, Vijay K. Shah
Artificial Intelligence · Cross-listed from cs.CL
CREDENCE: Claim Reduction for Decomposition & Enhanced Credibility – Semantic Metrics and Convergence Analysis
Phuong Huu Vu Tran, Thuan Duc Mai and Bach Xuan Le
Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking. Prior work has relied on
token-overlap (Jaccard) metrics that systematically underestimate decomposition quality for paraphrastic claims, and has lacked formal termination analysis for the repair loop. We present Credence, a revised claim decomposition and evaluation framework addressing both shortcomings. Our contributions are: (1) Semantic-F1: we use BGE-large cosine similarity fidelity metric that resolves Jaccard's penalisation and improves downstream fact-checking accuracy; (2) Convergence
theorems: we formally characterise four properties of the repair pipeline, establishing that rule-based repair is monotone and finitely terminating under an oracle parser assumption; LLM-based self-repair is provably non-monotone and requires an early-exit guard; (3) Three evaluation
benchmarks spanning social-media, encyclopaedic, and news domains for cross-domain generalisation measurement; (4) Multi-model benchmarking across four decomposer models (3.8B-12B) and a closed API model. Experiments on SocialClaimSplit, WikiSplitBench, and ClaimDecompBench show that Semantic-F1 outperforms Jaccard-F1 by +15-32pp. EPR ranges from 0.94 to 1.00 on SocialClaimSplit and WikiSplitBench, while ClaimDecompBench includes lower base EPR cases (down to 0.824) due to harder news-domain constructions, and rule-repair reduces the Atomicity Violation Rate (AVR) by 47-100% relative to the base model without degrading fidelity.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Uncertainty-Aware Reward Modeling for Stable RLHF
Licheng Pan, Haocheng Yang, Haoxuan Li et al. (+7 more)
Reinforcement learning from human feedback (RLHF) aligns large
language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamental challenges: (1) reward models cannot signal when their predictions are unreliable, since they usually act as deterministic point
estimators; and (2) modern group-based policy optimization can amplify unreliable reward signals, as exemplified by GRPO's uniform treatment of rewards during advantage computation. As policies explore increasingly diverse responses, these two limitations create a critical vulnerability: unreliable reward estimates may be granted disproportionate influence, triggering severe reward hacking. We propose Uncertainty-Aware Reward Modeling (UARM), which equips reward models with calibrated uncertainty via
quantile-based conformal prediction and reweights GRPO advantages through heteroscedastic variance decomposition. Experiments across HelpSteer, UltraFeedback, and PKU-SafeRLHF demonstrate that UARM significantly improves reward model calibration, reduces reward hacking, and enhances downstream
alignment quality compared to standard GRPO and uncertainty-agnostic baselines.
Read the full abstract ▾
All authors Licheng Pan, Haocheng Yang, Haoxuan Li, Yichen Sun, Yunsheng Lu, Shijian Wang, Lei Shen, Yuan Lu, Zhixuan Chu, Hao Wang
Artificial Intelligence
Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery
Anushree Sinha, Srivaths Ranganathan, Abhishek Dharmaratnakar et al. (+1 more)
Autonomous Large
Language Model (LLM)
agents are increasingly deployed in electronic discovery (e-discovery), where compounding errors across multi-step
reasoning chains can constitute legal malpractice. Unlike single-turn
retrieval, agentic workflows operating over privileged document corpora exhibit a class of failure we term "trajectory collapse": an early misclassification silently propagates, rendering an entire privilege review invalid. This paper makes three contributions. First, we propose a structured taxonomy of agentic failures in legal information
retrieval, organized by functional stage. Second, we introduce a four-layer verification architecture – spanning planning,
reasoning, execution, and uncertainty quantification – designed to intercept these failures before they compound. Third, we present a preliminary simulation study on a synthetic e-discovery corpus that demonstrates how mandatory Human-on-the-Loop (HOTL) escalation thresholds reduce privilege-waiver risk relative to fully autonomous baselines. Our results suggest that calibrated uncertainty thresholds can reduce privilege-waiver risk by up to 61% versus fully autonomous deployment, while routing fewer than one quarter of documents to attorney review.
Read the full abstract ▾
All authors Anushree Sinha, Srivaths Ranganathan, Abhishek Dharmaratnakar, Debanshu Das
Artificial Intelligence
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
Sajib Acharjee Dip, Dawei Zhou and Liqing Zhang
Test-time
reasoning is increasingly used as a serving-time control knob, but extra
reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes. We study this as a deployment allocation problem rather than a new-verifier problem. We introduce \sevra, Selective Verification for
Reasoning Allocation, a serving-layer controller that decides whether to preserve a frozen solver's initial answer or invoke active verification. Using a frozen Qwen3-4B solver, we log intervention outcomes and train recoverability-aware gates from serving-visible attempt state. On \mathfive, selective verification reaches 76.3% accuracy, compared with 75.5% for always verifying, while reducing post-generation
tokens by 26.8% and harmful flips from 2.2% to 1.0%. However, an 8,192-
token initial solve reaches 76.0% accuracy with 28% fewer total model
tokens, showing that selective recovery is useful but not the best tested cost frontier. In frozen transfer to \gsm, the selective policy verifies only 3.0% of examples, improves accuracy from 93.4% to 94.5%, and reduces verification
tokens by 91.2% relative to always verifying; again, a longer initial solve matches its accuracy with fewer realized
tokens. On CommonsenseQA, always-on verification hurts, while Self-Consistency@5 improves accuracy at about five times the realized
token cost. The resulting deployment rule is: tune the initial budget first, then use selective recovery when explicit checks, bounded retries, auditability, or regression-risk control matter.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number
Zijie Meng
Transferring the camera motion of a reference
video to a freshly generated one lets creators reuse cinematic moves. Yet reference and target often live at incompatible scales – a sweep across a
galaxy versus a nudge across a desk – and naively reusing the recovered trajectory yields either imperceptible or violently exaggerated motion. We trace this to a
geometric fact: translation-induced image motion scales as ||T||/Z, so a
monocular trajectory is meaningful only up to a depth-scale gauge. We distill this into the Parallax Number Pi = ||Delta T|| / Zbar, a dimensionless, gauge-invariant descriptor of how strongly a camera move is felt, and prove that it – not the raw trajectory – is the quantity that scale-faithful transfer must preserve. ParaScale is a plug-and-play module that reads Pi off any reference
video and re-realizes it against the target scene's own depth, per frame, leaving rotation untouched. Sitting between pose extraction and pose injection, it requires no retraining and drops into any pose-conditioned generator. We further introduce the Parallax Consistency Error (PCE), a scale-symmetric metric that – unlike the similarity-aligned TransErr – exposes scene-scale mismatch. Across scale regimes spanning four orders of magnitude and multiple backbones, ParaScale keeps the realized parallax on the identity line and cuts PCE by more than 3x over uncalibrated transfer with no loss of visual fidelity.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.DB
Policy-aware Vector Search: A Vision for Fine Grained Access Control in Vector Databases
Lakshmi Sahithi Yalamarthi and Primal Pappachan
Vector databases are increasingly used in security sensitive contexts with
Retrieval Augmented Generation and organizational AI pipelines; however, their security capabilities remain limited. Specifically, Fine-grained Access Control (FGAC) which is required to ensure that data access adheres to user-specific policies is not fully supported in modern vector databases. Unlike relational databases, vector databases combine structured and unstructured attributes to provide semantic, approximate query results, which complicates FGAC implementation. This creates an inherent tension between enforcing FGAC policies correctly, achieving high ANN search recall and maintaining low query latency. In this paper, we present a
vision for Policy-aware Vector Search by formalizing the FGAC policy model in vector databases as well as the enforcement problem. We compare various enforcement strategies, present preliminary findings, and identify key open challenges for future research in policy-aware vector search.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.AS
Improving End-to-End Speech Recognition for Dysarthric Speech through In-Domain Data Augmentation
Paban Sapkota, Hemant Kumar Kathania, Sudarsana Reddy Kadiri et al. (+1 more)
Dysarthric
speech recognition is crucial for facilitating effective communication among individuals with dysarthria. However, accurately recognizing dysarthric
speech poses significant challenges due to varying severity levels and limited data availability. In this paper, we explore data augmentation techniques for dysarthric automatic
speech recognition (ASR) systems by fine-tuning the End-to-End pre-trained Wav2Vec2 model, with a specific focus on severity levels. To address the challenges of data scarcity and the need for extensive data in fine-tuning pre-trained ASR systems for dysarthric
speech, we investigate four prominent data augmentation methods: Speaking-Rate Modification (SRM), Pitch Modification (PM), Formant Modification (FM), and vocal tract Length Perturbation (VTLP), tailored to different aspects of dysarthria. The study uses individually fine-tuned Wav2Vec2 models for each severity class as baseline systems. Additionally, we conducted severity-specific fine-tuning of the ASR model using augmented data. Results demonstrate distinct efficacy patterns for each augmentation technique across severity levels. The best WERs were achieved with SRM ($s$=0.8) for low (9.02%) and medium (38.11%) severities, and with PM ($\tau$=0.8) for high severity (55.15%), reflecting relative improvements of 30.02%, 16.64%, and 15.47%, respectively. These results confirm the effectiveness of the augmentation methods in improving dysarthric ASR performance.
Read the full abstract ▾
All authors Paban Sapkota, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan
Artificial Intelligence · Cross-listed from cs.SE
Agentic Electronic Design Automation: A Handoff Perspective
Jiawei Liu, Peiyi Han, Yuntao Lu et al. (+3 more)
Electronic design automation (EDA) is multi-stage and handoff-heavy, relying on transfers among humans, design artifacts, and multiple tools. LLM-based
agents now participate in these transfers, yet the resulting research landscape is highly fragmented and lacks a unified perspective. This survey adopts the primary input–output pair as its organizing lens: for each
agent system, we analyze its primary, supporting, and intermediate handoff objects and classify it according to the provenance of its primary input and the consumer boundary of its primary output. Intra-stage systems operate on objects within a single EDA stage, inter-stage systems transform EDA-native artifacts into forms usable by downstream stages, and extra-stage systems translate human intent into EDA artifacts. Based on this taxonomy, we survey 115 representative systems and examine them along multiple dimensions, including research trends,
benchmarks, and model mechanisms. Finally, we outline an agentic EDA protocol roadmap and discuss open problems for future research.
Read the full abstract ▾
All authors Jiawei Liu, Peiyi Han, Yuntao Lu, Su Zheng, Fengyu Yan, Bei Yu
Artificial Intelligence · Cross-listed from eess.AS
Systematic Study of Dysarthric Speech Recognition: Spectral Features and Acoustic Models
Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo et al. (+2 more)
The challenge associated with recognizing dysarthric
speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric
speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric
speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65% relative improvement in isolated word recognition and a 4.63% relative improvement in sentence recognition for dysarthric
speech, compared to previous research. This improvement effectively compensates for
speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.
Read the full abstract ▾
All authors Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo, Sudarsana Reddy Kadiri, Shrikanth Narayanan
Artificial Intelligence · Cross-listed from eess.AS
Cross-Dataset, Age, and Gender Generalization: A Comprehensive Analysis of Fine-Tuning Strategies for Low-Resource Children's ASR
Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri et al. (+1 more)
The challenge associated with recognizing dysarthric
speech primarily arises from pronounced acoustic variability attributed to impaired articulatory precision. Past research has demonstrated improved recognition through the use of hybrid DNN/HMM sequence discriminative training. This paper presents a comprehensive investigation of various combinations of acoustic features tailored to different Acoustic Models, offering suitable feature selections for each. The incorporation of Pitch features notably improved recognition performance, especially for sentence recognition tasks involving dysarthric
speech. Through a systematic examination of the TORGO database, we have demonstrated the potential to enhance the performance of the state-of-the-art Factorized Time Delay Neural Network (F-TDNN) model for recognizing dysarthric
speech. Our methods, implemented with the F-TDNN model, resulted in a 4.65% relative improvement in isolated word recognition and a 4.63% relative improvement in sentence recognition for dysarthric
speech, compared to previous research. This improvement effectively compensates for
speech variability, attributable to our deliberate selection of the number of overlapping frames between consecutive training example chunks.
Read the full abstract ▾
All authors Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri, Shrikanth Narayanan
Artificial Intelligence
CombEval: A Framework for Evaluating Combinatorial Counting in Large Language Models
Yuxu Zhou, Ondřej Kuželka, Yuyi Wang et al. (+2 more)
We present CombEval, a dynamic
benchmark for evaluating combinatorial counting in large
language models. CombEval represents each problem as a typed Cofola specification over entities, combinatorial objects, object dependencies, and constraints, enabling controlled generation of natural-
language counting problems with exact solver-verified answers. Unlike static collections, CombEval supports systematic variation of object type, entity scale, constraint count, and
reasoning depth. We evaluate 11 LLMs under direct and code-augmented settings and find that models remain brittle on ordered objects, indistinguishable elements, relatively positional constraints, and nested object dependencies. Error analysis further identifies failures in constraint interpretation and counting principles. CombEval provides a diagnostic testbed for studying when and why LLMs fail at combinatorial
reasoning. The code and generated
benchmark suites are publicly available at https://github.com/YuxuZhou-CN/combination-problem-generation.
Read the full abstract ▾
All authors Yuxu Zhou, Ondřej Kuželka, Yuyi Wang, Yuanhong Wang, Yi Chang
Artificial Intelligence
ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?
Jiajun Li, Mingshu Cai, Yixuan Li et al. (+5 more)
Large
language models are increasingly deployed as autonomous
agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear. Existing OR evaluations often decouple modeling from solving, rely on pre-formalized or text-only instances, and rarely test the full workflow from operational artifacts to validated decisions. In this work, we introduce ORAgentBench, an execution-grounded
benchmark for evaluating autonomous
agents on challenging end-to-end operations research tasks. It contains 107 human-reviewed tasks across diverse operational scenarios, each packaged in an isolated environment with a natural-
language brief, multi-file data, configuration artifacts, and a required submission schema.
Agents must write and run solution code, and their submissions are evaluated by hidden validators for schema validity, hard-constraint feasibility, and normalized objective quality. Experiments with fourteen frontier
agent-model configurations show that current
agents remain far from reliable OR practice. The best
agent passes only 35.51% of all tasks and 20.59% of hard tasks, and many feasible submissions still fall below the required quality threshold. Failure analysis further shows that errors are dominated by strategic weaknesses, including missed operational rules, brittle formulations, weak feasible-solution construction, and insufficient solution improvement. OR-specific procedural skills increase hard-task feasibility, but do not reliably improve solution quality or pass rate. These results suggest that progress in OR
agents requires moving beyond plausible optimization code toward dependable, high-quality operational decision-making.
Read the full abstract ▾
All authors Jiajun Li, Mingshu Cai, Yixuan Li, Yu Ding, Ran Hou, Guanyu Nie, Xiongwei Han, Wanyuan Wang
Artificial Intelligence
AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA
Aravind Narayanan and Shaina Raza
Financial chart question answering in regulated settings demands more than accuracy: practitioners must know which answers to trust before acting on them, and many institutions cannot send client data to external model providers. Yet existing chart-QA
agents are accuracy-focused and opaque, and most assume proprietary API access; to our knowledge, none combines auditability with on-premise deployability without significant accuracy compromise. We present AgentFinVQA, a multi-
agent pipeline that decomposes each query into planning, OCR, legend grounding, visual inspection, and verification, recording every step in a traceable Model Evaluation Packet (MEP) per sample. On FinMME, AgentFinVQA improves $+7.68$ pp over a primary-backbone matched zero-shot baseline with a proprietary backbone (Gemini-3 Flash; 71.24% vs. 63.56%, McNemar $p \approx 1.1 \times 10^{-16}$), and $+4.84$ pp with open-weights Qwen3.6-27B-FP8 served locally. The verifier's verdict also serves as a useful confidence signal (68.2% vs. 55.6% exact accuracy on confirmed vs. revised answers), enabling human-in-the-loop review routing. Error analysis shows that question misunderstanding, legend confusion and extraction error account for nearly two-thirds of failures and are the categories least detected by the verifier, identifying clear directions for future work. Together these results show that auditable, on-premise financial chart QA is practical and that the open-weights system keeps most of the accuracy gains while enabling full data residency. We release our code to support reproducible evaluation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from hep-ex
Towards Engineering Scaling Laws with Pretraining Data Composition
Jan-Lucas Uslu, Kevin Greif, Daniel Whiteson et al. (+1 more)
Neural scaling laws describe how model performance improves as a power law in compute, model size, and
dataset size. While well-established for large
language models, these relationships are emerging for large models in particle physics. As with
language, empirical studies show that the performance scales as a power law. However, unlike natural
language or image domains, fundamental physics has high-fidelity simulators that produce synthetic data cheaply. This favors scaling regimes where additional data is cheaper than additional parameters, and allows the pretraining
dataset itself to be engineered to influence the scaling. For the task of classifying hadronic jets produced in collisions of high-energy particle beams, we show that the scaling behavior can be engineered towards requiring more data rather than larger models by inclusion of pretraining data which is more diverse and better aligned with the downstream classification task.
Read the full abstract ▾
All authors Jan-Lucas Uslu, Kevin Greif, Daniel Whiteson, Benjamin Nachman
Artificial Intelligence
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
Xuanzhi Feng, Zhengyang Li, Zeyu Liu et al. (+6 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large
Language Model (LLM)
reasoning; however, it faces a fundamental optimization instability: uniform
token updates precipitate
entropy collapse, leading to premature convergence to suboptimal strategies, whereas excessive Shannon
Entropy maximization can cause
entropy explosion, driving blind exploration toward incoherent
reasoning chains. To resolve this dichotomy, we introduce the Independent Combinatorial
Tokens (ICT) framework, which shifts the optimization focus from scalar uncertainty to the distributional properties of
token logits. By leveraging the Jensen-Shannon (JS) divergence between
token logits distributions, ICT identifies
tokens with distinctive distributional patterns as critical branching points for guiding effective exploration in LLM
reasoning. Our theoretical analysis, grounded in both Shannon and second-order Rényi
entropy, proves that selectively updating on these
tokens regulates policy concentration: it reduces the overall distribution uncertainty measured by Shannon
entropy, while controlling probability concentration captured by second-order Rényi
entropy. This dual effect prevents over-concentrated
token generation from weakening exploration and effectively stabilizes the training landscape. Empirical results demonstrate that updating only the top 10% of unique
tokens on Qwen2.5 (0.5B/1.5B/7B) models yields an average pass@4 improvement of 4.58%, with a maximum gain of 14.9%, over GRPO, 20-
Entropy, and STAPO baselines across seven
benchmarks spanning math, commonsense, and Olympiad-level problems.
Read the full abstract ▾
All authors Xuanzhi Feng, Zhengyang Li, Zeyu Liu, Haoxi Li, Yuming Jiang, Bing Guo, Jingcai Guo, Jie Zhang, Song Guo
Artificial Intelligence · Cross-listed from cs.RO
Data Standards for Humanoid Robotics: The Missing Infrastructure for Physical AI
Shaoshan Liu, Xiugong Qin, Xuan Wu et al. (+4 more)
The scalability of
humanoid robots will depend not only on models and hardware, but also on whether physical experience can accumulate across
robots, tasks, organizations, and time. Drawing on the authors' work in developing ISO/WD 26264-1,
Humanoid robot datasets – Part 1: General requirements, within ISO/TC 299/WG 16, this article argues that data standards are becoming foundational infrastructure for Physical AI. We develop three insights. First,
humanoid robot data is
embodied interaction data, not a collection of isolated digital samples; a useful
dataset must preserve the relationship among
robot body, action, task, scene, execution trace, and outcome. Second, its value depends on physical coherence:
multimodal streams are reusable only when timing, coordinate frames, calibration, kinematics, units, and synchronization assumptions remain inspectable. Third, the main bottleneck is not only data scarcity, but non-cumulative data caused by high collection costs, data silos, and inconsistent evaluation. We argue that
humanoid robot data standards address these bottlenecks by making
embodied experience interpretable, shareable, traceable, and reusable. A general standard should provide horizontal infrastructure for lifecycle management, metadata, provenance, quality, versioning, and traceability, while capability-specific parts should define domain grammar for manipulation, locomotion, human-
robot interaction, cognition, and future
humanoid capabilities. As AI moves from screens into bodies, data standards must evolve from organizing digital information to structuring physical interaction.
Read the full abstract ▾
All authors Shaoshan Liu, Xiugong Qin, Xuan Wu, Xuan Xia, Ning Ding, Jialu Liu, Jie Tang
Artificial Intelligence
Optimal Scheduling in a Question-Answering Forum of Knowledge Workers
Rohit Negi and Mustafa Yilmaz
As individuals turn to the Internet to find answers to questions they may have, several Question Answering (QA) forums have evolved, where users knowledgeable in certain topics can contribute their expertise to answering these requests for information. While these are currently volunteer based, we consider a future version employing knowledge workers who are experts in certain topics. In such a system, the request-answer processes forming the queuing system may utilize schedulers that assign requests in different topics to the experts in the forum, who may be able to answer them according to their expertise levels in different topics. With this model, we calculate the capacity of the system for handling the requests while keeping the system stable, and design schedulers that achieve capacity. We also investigate how collaboration between experts in answering requests can potentially increase capacity.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
SafeSpec: Fast and Safe LLM via Dynamic Reflective Sampling
Haotian Xu, Zeyang Zhang, Linbao Li et al. (+3 more)
Speculative inference accelerates large
language model (LLM) decoding but provides no inherent safety guarantees. Existing safety defenses are largely incompatible with speculative inference: they either introduce additional computation or disrupt the draft-verify mechanism, negating acceleration benefits. This reveals a fundamental incompatibility between current safety methods and speculative decoding. We propose SafeSpec, a safety-aware speculative inference framework that integrates risk estimation directly into the verification process. SafeSpec attaches a lightweight latent safety head to the target model to jointly evaluate semantic validity and safety in a single forward pass. When unsafe generations are detected, SafeSpec applies rollback and safety-guided reflective multi-sampling to recover safe continuations rather than terminating generation. We model jailbreak attacks as distributional shifts over generative trajectories, where
adversarial prompts increase the probability of harmful continuations without eliminating safe ones. Under this model, SafeSpec performs risk-aware trajectory recovery within the speculative decoding process. Across multiple models and
adversarial benchmarks, SafeSpec achieves a substantially improved safety-efficiency trade-off. On Qwen3-32B, SafeSpec reduces attack success rates by 15% while preserving a 2.06x inference speedup on benign workloads, demonstrating that speculative acceleration and inference-time safety can be jointly optimized.
Read the full abstract ▾
All authors Haotian Xu, Zeyang Zhang, Linbao Li, Huadi Zheng, Yu Li, Cheng Zhuo