arXiv:2605.00789v1 Announce Type: cross Abstract: Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial GPU memory overhead due to the large number of vision tokens processed during the prefill stage. […]
AgentReputation: A Decentralized Agentic AI Reputation Framework
arXiv:2605.00073v1 Announce Type: new Abstract: Decentralized, agentic AI marketplaces are rapidly emerging to support software engineering tasks such as debugging, patch generation, and security auditing, often operating without centralized oversight. However, existing reputation mechanisms fail in this setting for three fundamental reasons: agents can strategically optimize against evaluation procedures; demonstrated competence does not reliably transfer […]
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
arXiv:2505.10887v3 Announce Type: replace Abstract: This paper introduces textscInfantAgent-Next, a generalist agent capable of interacting with computers in a multimodal manner, encompassing text, images, audio, and video. Unlike existing approaches that either build intricate workflows around a single large model or only provide workflow modularity, our agent integrates tool-based and pure vision agents within a […]
CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift
arXiv:2605.00074v1 Announce Type: new Abstract: DNA-synthesis providers screen incoming orders by searching the requested sequence against curated hazard lists. We show that this baseline collapses to a 100% false-flag rate when the hazardous sequence comes from a taxonomic family absent from the reference set: under Conformal Risk Control’s certified miss-rate constraint, a low-discrimination signal forces […]
Compiling Deterministic Structure into SLM Harnesses
arXiv:2604.17450v2 Announce Type: replace Abstract: Enterprise SLM deployment faces epistemic asymmetry: small models cannot self-correct reasoning errors, while frontier LLMs incur prohibitive costs and data sovereignty risks at scale. We propose Semantic Gradient Descent (SGDe), a teacher-student framework that compiles agentic workflows into discrete execution plans–DAG topologies, system prompts, and deterministic code. The trailing e […]
TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data
arXiv:2605.00060v1 Announce Type: new Abstract: We present TADI (Tool-Augmented Drilling Intelligence), an agentic AI system that transforms drilling operational data into evidence-based analytical intelligence. Applied to the Equinor Volve Field dataset, TADI integrates 1,759 daily drilling reports, selected WITSML real-time objects, 15,634 production records, formation tops, and perforations into a dual-store architecture: DuckDB for structured […]
Lightweight Domain Adaptation of a Large Language Model for Legal Assistance in the Indian Context
arXiv:2505.22003v2 Announce Type: replace-cross Abstract: In India, access to legal assistance for the general public has been observed to have a critical gap, as many citizens are not able to take full advantage of their legal rights due to limited access and awareness of apposite legal information. This paper thus introduces Legal Assist AI, a […]
EPITIME: A Computational Framework for Integral Epidemic Models with Structure-Preserving Discretizations
arXiv:2605.00067v1 Announce Type: new Abstract: We present EPITIME (EPidemic Integral models TIMe profile Explorer), a computational framework for the simulation of two classes of integral epidemic models: an age of infection model and an information dependent behavioural model. The framework combines structure preserving Non-Standard Finite Difference discretizations with modular implementations in MATLAB and Python, together […]
Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
arXiv:2510.09696v3 Announce Type: replace-cross Abstract: The increasing scale of Deep Neural Networks (DNNs) introduces the need for compression techniques such as pruning, quantization, and low-rank decomposition. While these methods are very effective at reducing memory, computation, and energy consumption, they may introduce severe accuracy degradation, which is often mitigated by using iterative, gradual compression. However, […]
Sure About That Line? Approaching Confidence-Based, Real-Time Line Assignment in Reading Gaze Data
arXiv:2605.00033v1 Announce Type: new Abstract: Remote and webcam-based eye tracking in multi-line reading suffers from various noise factors and layout ambiguity, precisely where real-time reading support needs reliable, per-fixation line assignment. Prior work largely addresses this challenge post hoc or by restricting behavior (e.g., disallowing re-reading), undermining interactive use. We propose CONF-LA (Confidence-score-based Online Fixation-to-Line […]
Can Small Language Models Handle Context-Summarized Multi-Turn Customer-Service QA? A Synthetic Data-Driven Comparative Evaluation
arXiv:2602.00665v3 Announce Type: replace-cross Abstract: Customer-service question answering (QA) systems increasingly rely on conversational language understanding. While Large Language Models (LLMs) achieve strong performance, their high computational cost and deployment constraints limit practical use in resource-constrained environments. Small Language Models (SLMs) provide a more efficient alternative, yet their effectiveness for multi-turn customer-service QA remains underexplored, […]
Toward Magnetic-Field-Free Quantum Computing and Quantum Reservoir Computing in Engineered Organic Materials: A Unified Framework from the 3-Layer Quantum Brain Hypothesis
arXiv:2605.00026v1 Announce Type: new Abstract: We extend the spin-vortex-induced loop-current (SVILC) qubit [Wakaura2017] and the 3-Layer Quantum Brain Hypothesis to engineered organic materials operated without any applied magnetic field. Four paths are proposed: (P1) a flavin–nitroxide radical-pair reservoir, (P2) a perchlorotriphenylmethyl (PTM) radical array in a covalent organic framework, (P3) the SVILC analogue on $kappa$-(BEDT-TTF)$_2$Cu[N(CN)$_2$]Br […]