IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings
arXiv:2603.05556v1 Announce Type: new
Abstract: Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic s...
Autocorrelation effects in a stochastic-process model for decision making via time series
arXiv:2603.05559v1 Announce Type: new
Abstract: Decision makers exploiting photonic chaotic dynamics obtained by semiconductor lasers provide an ultrafast approach to solving multi-armed bandit problems by using a temporal optical signal as the driving source for sequential decisions. In such syste...
RoboLayout: Differentiable 3D Scene Generation for Embodied Agents
arXiv:2603.05522v1 Announce Type: new
Abstract: Recent advances in vision language models (VLMs) have shown strong potential for spatial reasoning and 3D scene layout generation from open-ended language instructions. However, generating layouts that are not only semantically coherent but also feasi...
Real-Time AI Service Economy: A Framework for Agentic Computing Across the Continuum
arXiv:2603.05614v1 Announce Type: new
Abstract: Real-time AI services increasingly operate across the device-edge-cloud continuum, where autonomous AI agents generate latency-sensitive workloads, orchestrate multi-stage processing pipelines, and compete for shared resources under policy and governa...
Reasoning Models Struggle to Control their Chains of Thought
arXiv:2603.05706v1 Announce Type: new
Abstract: Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To m...
Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery
arXiv:2603.05860v1 Announce Type: new
Abstract: Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their decisions through a sequence of specialized procedures. While LLM-based a...
The World Won't Stay Still: Programmable Evolution for Agent Benchmarks
arXiv:2603.05910v1 Announce Type: new
Abstract: LLM-powered agents fulfill user requests by interacting with environments, querying data, and invoking tools in a multi-turn process. Yet, most existing benchmarks assume static environments with fixed schemas and toolsets, neglecting the evolutionary...
Operational stability for mission-critical ML systems
If observability tools can capture everything happening in modern infrastructure, why can’t AI systems clearly explain the decisions they recommend? This tension lies at the heart of the growing explainability crisis in applied AI.
Decorrelating the Future: Joint Frequency Domain Learning for Spatio-temporal Forecasting
arXiv:2603.04418v1 Announce Type: new
Abstract: Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain approaches such a...
Machine Learning for Complex Systems Dynamics: Detecting Bifurcations in Dynamical Systems with Deep Neural Networks
arXiv:2603.04420v1 Announce Type: new
Abstract: Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these shifts typic...
Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes
arXiv:2603.04426v1 Announce Type: new
Abstract: Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However, existing formul...
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
arXiv:2603.04427v1 Announce Type: new
Abstract: Standard transformer attention uses identical dimensionality for queries, keys, and values ($d_q = d_k = d_v = \dmodel$). Our insight is that these components serve fundamentally different roles, and this symmetry is unnecessary. Queries and keys prod...
arXiv:2603.04448v1 Announce Type: new
Abstract: Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``...
Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding
arXiv:2603.04514v1 Announce Type: new
Abstract: Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating refinement ...
Discovering mathematical concepts through a multi-agent system
arXiv:2603.04528v1 Announce Type: new
Abstract: Mathematical concepts emerge through an interplay of processes, including experimentation, efforts at proof, and counterexamples. In this paper, we present a new multi-agent model for computational mathematical discovery based on this observation. Our...
arXiv:2603.04549v1 Announce Type: new
Abstract: LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of conversatio...
GenCtrl -- A Formal Controllability Toolkit for Generative Models
As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains unanswered: are these models truly controllable in the first place...
Flow models parameterized as time-dependent velocity fields can generate data from noise by integrating an ODE. These models are often trained using flow matching, i.e. by sampling random pairs of noise and target points (x0,x1)(\mathbf{x}_0, \mathbf{x}_1)(x0,x1) and ensuring that the velocity fie...
Multi-Frequency Fusion for Robust Video Face Forgery Detection
Current face video forgery detectors use wide or dual-stream backbones. We show that a single, lightweight fusion of two handcrafted cues can achieve higher accuracy with a much smaller model. Based on the Xception baseline model (21.9 million parameters), we build two detectors: LFWS, which adds a ...
RAG that remembers: How AI is learning from every query
What if search systems didn’t just retrieve information, but remembered what worked? Expanded Relevance Memory (ERM) proves that query expansion and document expansion are mathematically equivalent, unlocking a powerful shift...
Knowledge Graph and Hypergraph Transformers with Repository-Attention and Journey-Based Role Transport
arXiv:2603.03304v1 Announce Type: new
Abstract: We present a concise architecture for joint training on sentences and structured data while keeping knowledge and language representations separable. The model treats knowledge graphs and hypergraphs as structured instances with role slots and encodes...
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
arXiv:2603.03378v1 Announce Type: new
Abstract: Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action executi...
RADAR: Learning to Route with Asymmetry-aware DistAnce Representations
arXiv:2603.03388v1 Announce Type: new
Abstract: Recent neural solvers have achieved strong performance on vehicle routing problems (VRPs), yet they mainly assume symmetric Euclidean distances, restricting applicability to real-world scenarios. A core challenge is encoding the relational features in...
Towards Improved Sentence Representations using Token Graphs
arXiv:2603.03389v1 Announce Type: new
Abstract: Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling methods like mean or max aggregation treat tokens as an independent set,...