Algebraic Integer Quantization for Machine Learning Applications
arXiv:2610.12494v1 Announce Type: new
Abstract: In this article, we propose algebraic integer number formats (AINF) as a framework for highly configurable and accurate compressed computation. A key property of AINF is its straightforward reduction to purely integer arithmetic, enabling error-free m...
Kairos: Toward a Byte-Level Foundation Model for Every Modality
arXiv:2610.12495v1 Announce Type: new
Abstract: Small language models trained on a single local machine leave little room for architectural trial and error. Kairos combines bidirectional gated-DeltaNet linear attention and sliding-window attention over shared projections (LiZAttention2), block-wise...
An Input-Dependent Readout Phase for Resonant Sequence Models
arXiv:2610.12496v1 Announce Type: new
Abstract: Sequence models with a fixed-size state avoid the quadratic cost of attention, but face a design choice. An input-dependent state transition gives content-dependent memory at the cost of FFT-based training, while a fixed transition keeps the O(T log T...
CircuitTree: Composing Circuits into A Syllable Transcriber
arXiv:2610.12520v1 Announce Type: new
Abstract: The goal of circuit discovery is to decompose a monolithic neural network into tiny modular subnetworks which are interpretable in the sense that each does an identifiable subtask. We develop a practical method for composing arbitrarily many circuits ...
Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance
arXiv:2610.12493v1 Announce Type: new
Abstract: Explainable Artificial Intelligence (XAI) tools have often been presented as methods to increase trust in machine learning models by making aspects of their algorithms more human-understandable. However, evidence accumulated over the last decade point...
Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning
arXiv:2610.12593v1 Announce Type: new
Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning ...
SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
arXiv:2610.12596v1 Announce Type: new
Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and ...
Analyzing thousands of human-AI conversations, a new study shows that people are turning to chatbots for increasingly critical tasks – and that productive outcomes depend on how the collaboration unfolds.
Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged
Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation. With MT evaluation spanning a large number of language pairs, domains and levels of annotation granularity, LLMs must be thoroughly evaluated a...
Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost, limited elasticity, and long wait times under resource constraints. At the same time, modern Apple Silicon–based macOS devices are equipped with power...
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it with fixed-interval compaction triggered at a token threshold. Such triggers pay no heed to trajectory...
When you're building an AI agent for 70 million users, the stakes are a little different than when you're prototyping something for a demo. The margin for error shrinks. The edge cases multiply. And the things that feel like minor details in development become very real problems in production...
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
arXiv:2610.10590v1 Announce Type: new
Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetting: the acting model selects previously observed tool results, replaces each with a short note at i...
SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
arXiv:2610.10571v1 Announce Type: new
Abstract: Electroencephalography (EEG) provides a non-invasive measure of ongoing neural activity, but building general-purpose EEG models remains challenging due to the heterogeneity of subjects, devices, and electrode montages. Existing EEG foundation models ...
Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs
arXiv:2610.10594v1 Announce Type: new
Abstract: Activation probes that monitor deployed language models are trained on synthetic conversations, and how many a probe needs is open. We trace learning curves over 10-590 synthetic samples for three monitoring concepts, high-stakes situations, replies h...
Temporal transformer CAN encoder with federated lightweight heads for anomaly detection
arXiv:2610.10613v1 Announce Type: new
Abstract: Modern vehicles rely on large numbers of Electronic Control Units (ECUs) that constantly exchange information over the Controller Area Network (CAN) bus. Due to the rapidity, structure, and repetition of this communication, even slight variations in t...
When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry
arXiv:2610.10616v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) language models produce routing information during inference that may be logged or exposed for monitoring, debugging, load analysis, and safety auditing. Unlike ordinary model outputs, this telemetry reveals a view of the mode...
An Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
arXiv:2610.10541v1 Announce Type: new
Abstract: Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration. In metadata-only Semantic Table Interpretation (STI), where cell values are unavailable, noisy, or unsui...
Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
arXiv:2610.10549v1 Announce Type: new
Abstract: Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and legal restrictions on enterprise systems, data, and database schemas. Tabular data synthesis offers a ...
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
arXiv:2610.10629v1 Announce Type: new
Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is reviewable only if it ...
Verification and Self-Improvement in Agentic AI: Foundations and Limits
arXiv:2610.10611v1 Announce Type: new
Abstract: Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs. A performance score does not distinguish these mechanisms. We compare these changes through bounded verification with h...
Transferability and operational reliability of a Prithvi crop classification foundation model under phenological and geographic shift across three continents
arXiv:2610.08810v1 Announce Type: new
Abstract: Fine-tuned geospatial foundation models (GeoFMs) pretrained on large satellite archives have been shown to improve crop classification accuracy and geographic transferability. However, their operational performance beyond the training distribution rem...