Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
arXiv:2602.16943v1 Announce Type: new Abstract: Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure text-level refusal behavior, leaving a critical...
HQFS: Hybrid Quantum Classical Financial Security with VQC Forecasting, QUBO Annealing, and Audit-Ready Post-Quantum Signing
arXiv:2602.16976v1 Announce Type: new Abstract: Here's the corrected paragraph with all punctuation and formatting issues fixed: Financial risk systems usually follow a two-step routine: a model predicts return or risk, and then an optimizer makes a decision such as a...
M2F: Automated Formalization of Mathematical Literature at Scale
arXiv:2602.17016v1 Announce Type: new Abstract: Automated formalization of mathematics enables mechanical verification but remains limited to isolated theorems and short snippets. Scaling to textbooks and research papers is largely unaddressed, as it requires managing cross-file dependencies, resolving imports, and ensuring...
Sales Research Agent and Sales Research Bench
arXiv:2602.17017v1 Announce Type: new Abstract: Enterprises increasingly need AI systems that can answer sales-leader questions over live, customized CRM data, but most available models do not expose transparent, repeatable evidence of quality. This paper describes the Sales Research Agent in...
IntentCUA: Learning Intent-level Representations for Skill Abstraction and Multi-Agent Planning in Computer-Use Agents
arXiv:2602.17049v1 Announce Type: new Abstract: Computer-use agents operate over long horizons under noisy perception, multi-window contexts, evolving environment states. Existing approaches, from RL-based planners to trajectory retrieval, often drift from user intent and repeatedly solve routine subproblems, leading to error...
RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
arXiv:2602.17053v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability and trust. We introduce a formal framework for reasoning faithfulness, defined...
Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning
arXiv:2602.17062v1 Announce Type: new Abstract: Value decomposition is a core approach for cooperative multi-agent reinforcement learning (MARL). However, existing methods still rely on a single optimal action and struggle to adapt when the underlying value function shifts during training, often...
Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization
arXiv:2602.17066v1 Announce Type: new Abstract: We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning approaches that require predefined difficulty metrics or hard...
Toward Trustworthy Evaluation of Sustainability Rating Methodologies: A Human-AI Collaborative Framework for Benchmark Dataset Construction
arXiv:2602.17106v1 Announce Type: new Abstract: Sustainability or ESG rating agencies use company disclosures and external data to produce scores or ratings that assess the environmental, social, and governance performance of a company. However, sustainability ratings across agencies for a single...
All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection in LLM Backtesting
arXiv:2602.17234v1 Announce Type: new Abstract: To evaluate whether LLMs can accurately predict future events, we need the ability to \textit{backtest} them on events that have already resolved. This requires models to reason only with information available at a specified past...
Evaluating Monolingual and Multilingual Large Language Models for Greek Question Answering: The DemosQA Benchmark
arXiv:2602.16811v1 Announce Type: new Abstract: Recent advancements in Natural Language Processing and Deep Learning have enabled the development of Large Language Models (LLMs), which have significantly advanced the state-of-the-art across a wide range of tasks, including Question Answering (QA). Despite...
Meenz bleibt Meenz, but Large Language Models Do Not Speak Its Dialect
arXiv:2602.16852v1 Announce Type: new Abstract: Meenzerisch, the dialect spoken in the German city of Mainz, is also the traditional language of the Mainz carnival, a yearly celebration well known throughout Germany. However, Meenzerisch is on the verge of dying out-a...
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
arXiv:2602.16938v1 Announce Type: new Abstract: The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but may fail to perform well in the real...
Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry
arXiv:2602.16959v1 Announce Type: new Abstract: Classical Persian poetry is a historically sustained archive in which affective life is expressed through metaphor, intertextual convention, and rhetorical indirection. These properties make close reading indispensable while limiting reproducible comparison at scale. We present...
Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
arXiv:2602.17003v1 Announce Type: new Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail of their intent, practical web agents must be able to interpret ambiguous queries by inferring user...
The Emergence of Lab-Driven Alignment Signatures: A Psychometric Framework for Auditing Latent Bias and Compounding Risk in Generative AI
arXiv:2602.17127v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from standalone chat interfaces to foundational reasoning layers in multi-agent systems and recursive evaluation loops (LLM-as-a-judge), the detection of durable, provider-level behavioral signatures becomes a critical requirement for safety...
What Makes a Good Doctor Response? An Analysis on a Romanian Telemedicine Platform
arXiv:2602.17194v1 Announce Type: new Abstract: Text-based telemedicine has become a common mode of care, requiring clinicians to deliver medical advice clearly and effectively in writing. As platforms increasingly rely on patient ratings and feedback, clinicians face growing pressure to maintain...
Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study
arXiv:2602.17262v1 Announce Type: new Abstract: Human self-report questionnaires are increasingly used in NLP to benchmark and audit large language models (LLMs), from persona consistency to safety and bias assessments. Yet these instruments presume honest responding; in evaluative contexts, LLMs can...
Towards Cross-lingual Values Assessment: A Consensus-Pluralism Perspective
arXiv:2602.17283v1 Announce Type: new Abstract: While large language models (LLMs) have become pivotal to content safety, current evaluation paradigms primarily focus on detecting explicit harms (e.g., violence or hate speech), neglecting the subtler value dimensions conveyed in digital content. To...
Representation Collapse in Machine Translation Through the Lens of Angular Dispersion
arXiv:2602.17287v1 Announce Type: new Abstract: Modern neural translation models based on the Transformer architecture are known for their high performance, particularly when trained on high-resource datasets. A standard next-token prediction training strategy, while widely adopted in practice, may lead to...
Same Meaning, Different Scores: Lexical and Syntactic Sensitivity in LLM Evaluation
arXiv:2602.17316v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has established standardized evaluation benchmarks as the primary instrument for model comparison. Yet, their reliability is increasingly questioned due to sensitivity to shallow variations in input prompts....
The Role of the Availability Heuristic in Multiple-Choice Answering Behaviour
arXiv:2602.17377v1 Announce Type: new Abstract: When students are unsure of the correct answer to a multiple-choice question (MCQ), guessing is common practice. The availability heuristic, proposed by A. Tversky and D. Kahneman in 1973, suggests that the ease with which...
Bridging the Domain Divide: Supervised vs. Zero-Shot Clinical Section Segmentation from MIMIC-III to Obstetrics
arXiv:2602.17513v1 Announce Type: new Abstract: Clinical free-text notes contain vital patient information. They are structured into labelled sections; recognizing these sections has been shown to support clinical decision-making and downstream NLP tasks. In this paper, we advance clinical section segmentation...
Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems
arXiv:2602.17542v1 Announce Type: new Abstract: Fine-grained skill representations, commonly referred to as knowledge components (KCs), are fundamental to many approaches in student modeling and learning analytics. However, KC-level correctness labels are rarely available in real-world datasets, especially for open-ended programming...
Modeling Distinct Human Interaction in Web Agents
arXiv:2602.17588v1 Announce Type: new Abstract: Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene,...
Sink-Aware Pruning for Diffusion Language Models
arXiv:2602.17664v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited from autoregressive (AR) LLMs, typically preserve attention sink tokens because AR sinks serve as stable...
Omitted Variable Bias in Language Models Under Distribution Shift
arXiv:2602.16784v1 Announce Type: cross Abstract: Despite their impressive performance on a wide variety of tasks, modern language models remain susceptible to distribution shifts, exhibiting brittle behavior when evaluated on data that differs in distribution from their training data. In this...
Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
arXiv:2602.16787v1 Announce Type: cross Abstract: Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in their causal reasoning ability. While recent work has demonstrated that labeled counterfactual tasks...
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
arXiv:2602.16819v1 Announce Type: cross Abstract: When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more various and complex tasks that involve other...
Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
arXiv:2602.16740v1 Announce Type: new Abstract: In mechanistic interpretability, recent work scrutinizes transformer "circuits" - sparse, mono or multi layer sub computations, that may reflect human understandable functions. Yet, these network circuits are rarely acid-tested for their stability across different instances...