arXiv:2604.12782v1 Announce Type: cross Abstract: While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we systematically investigate the spatial distribution of outliers and demonstrate a token-persistent structural clustering effect, where high-magnitude outliers […]
oxo-call: Documentation-grounded Skill Augmentation for Accurate Bioinformatics Command-line Generation with Large Language Models
arXiv:2604.12387v1 Announce Type: new Abstract: Command-line bioinformatics tools remain essential for genomic analysis, yet their diversity in syntax and parameterization presents a persistent barrier to productive research. We present oxo-call, a Rust-based command-line assistant that translates natural-language task descriptions into accurate tool invocations through two complementary strategies: documentation-first grounding, which provides the large language model […]
LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software
arXiv:2604.12994v1 Announce Type: cross Abstract: Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although existing automated program repair techniques primarily focus on repairing memory corruption vulnerabilities, they struggle with logical vulnerabilities because of their limited semantic understanding of the vulnerable code and […]
Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments
arXiv:2604.12459v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in politically sensitive environments, where memorisation of personal data or confidential content raises regulatory concerns under frameworks such as the GDPR and its Right to be Forgotten. Translating such legal principles into large-scale generative systems presents significant technical challenges. We introduce a lightweight […]
Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space
arXiv:2602.05971v2 Announce Type: replace-cross Abstract: Semantic representations can be framed as a structured, dynamic knowledge space through which humans navigate to retrieve and manipulate meaning. To investigate how humans traverse this geometry, we introduce a framework that represents concept production as navigation through embedding space. Using different transformer text embedding models, we construct participant-specific semantic […]
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
arXiv:2604.12461v1 Announce Type: new Abstract: LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of communication topologies has attracted increasing attention. In this paper, we investigate a critical privacy risk: MAS communication topologies can be […]
LoViF 2026 The First Challenge on Weather Removal in Videos
arXiv:2604.10655v2 Announce Type: replace-cross Abstract: This paper presents a review of the LoViF 2026 Challenge on Weather Removal in Videos. The challenge encourages the development of methods for restoring clean videos from inputs degraded by adverse weather conditions such as rain and snow, with an emphasis on achieving visually plausible and temporally consistent results while […]
Technical Report — A Context-Sensitive Multi-Level Similarity Framework for First-Order Logic Arguments: An Axiomatic Study
arXiv:2604.12534v1 Announce Type: new Abstract: Similarity in formal argumentation has recently gained attention due to its significance in problems such as argument aggregation in semantics and enthymeme decoding. While existing approaches focus on propositional logic, we address the richer setting of First-Order Logic (FOL), where similarity must account for structured content. We introduce a comprehensive […]
The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break
arXiv:2604.11978v1 Announce Type: new Abstract: Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic systems, these long-horizon failures remain poorly characterized, hindering principled diagnosis and comparison across domains. To address this gap, we introduce […]
Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents
arXiv:2604.12545v1 Announce Type: new Abstract: Improving policymaking is a central concern in public administration. Prior human subject studies reveal substantial cross-cultural differences in citizens’ emotional responses to red tape during policy implementation. While LLM agents offer opportunities to simulate human-like responses and reduce experimental costs, their ability to generate culturally appropriate emotional responses to red […]
Variation in Verification: Understanding Verification Dynamics in Large Language Models
arXiv:2509.17995v2 Announce Type: replace-cross Abstract: Recent advances have shown that scaling test-time computation enables large language models (LLMs) to solve increasingly complex problems across diverse domains. One effective paradigm for test-time scaling (TTS) involves LLM generators producing multiple solution candidates, with LLM verifiers assessing the correctness of these candidates without reference answers. In this paper, […]
IDEA: An Interpretable and Editable Decision-Making Framework for LLMs via Verbal-to-Numeric Calibration
arXiv:2604.12573v1 Announce Type: new Abstract: Large Language Models are increasingly deployed for decision-making, yet their adoption in high-stakes domains remains limited by miscalibrated probabilities, unfaithful explanations, and inability to incorporate expert knowledge precisely. We propose IDEA, a framework that extracts LLM decision knowledge into an interpretable parametric model over semantically meaningful factors. Through joint learning […]