Search: “routing”

arXiv:2512.23234v3 Announce Type: replace-cross Abstract: Infrared gas leak detection is important for industrial safety and environmental monitoring, but automatic detection remains challenging becau

arXiv:2606.03557v1 Announce Type: new Abstract: As generative AI capabilities expand, AI-driven virtual worlds face a growing architectural challenge. Users interact through in-world interfaces in mul

arXiv:2606.03486v1 Announce Type: cross Abstract: Large language models remain vulnerable to jailbreak attacks that hide harmful intent behind seemingly ordinary requests such as role-play, translatio

arXiv:2606.02398v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation,

arXiv:2606.01770v1 Announce Type: cross Abstract: Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infras

arXiv:2606.00671v1 Announce Type: new Abstract: We present AXIOM, a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning. In AXIOM, the language model function

arXiv:2606.01007v1 Announce Type: cross Abstract: Sparsely activated Mixture-of-Experts (MoE) models scale capacity via conditional computation, but distributed inference suffers from cross-GPU expert

arXiv:2606.00804v1 Announce Type: cross Abstract: Enterprise multi-agent systems increasingly expose multiple coordination patterns, but deployments often lack evidence for when to use consensus, deba

arXiv:2606.01660v1 Announce Type: new Abstract: Pre-propagation graph neural networks (PPGNNs) push all graph-dependent computation into a preprocessing step and train only on the resulting dense hop

arXiv:2606.01472v1 Announce Type: cross Abstract: High-stakes production document-generation systems require language models to be adaptive, evidence-grounded, and auditable. We present HOPM, a hierar

arXiv:2606.01065v1 Announce Type: cross Abstract: Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only evict

arXiv:2606.00651v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Models (LLMs) efficiently, enabling greater capacity with reduced computational cost by dy

arXiv:2606.02494v1 Announce Type: cross Abstract: Agentic systems entering production typically operate as partially integrated assemblies where structural defects, not task-level errors, dominate the

arXiv:2511.05650v2 Announce Type: replace-cross Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of diversity, yielding highly similar outputs across g

arXiv:2606.01101v1 Announce Type: cross Abstract: The quadratic complexity of self-attention remains a bottleneck for Large Language Models (LLMs) processing ultra-long contexts. The Naive Bayes Cogni

arXiv:2605.30538v1 Announce Type: new Abstract: Disasters are inevitable and increasingly costly, and effective response depends on querying structured tabular data: precise, information-dense records

arXiv:2605.30876v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregressive models, offering competitive performance whil

arXiv:2605.31363v1 Announce Type: new Abstract: Many languages are written in multiple scripts, requiring large language models (LLMs) to generate equivalent linguistic content in distinct orthographi

arXiv:2605.29467v1 Announce Type: cross Abstract: Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be pre

arXiv:2605.29606v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottl

arXiv:2605.29495v1 Announce Type: new Abstract: Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers

arXiv:2605.30207v1 Announce Type: new Abstract: The same prompt -- 'best CRM software' -- reaches AI assistants from buyers in widely different contexts: a solo founder, an enterprise VP, a UK SMB own

arXiv:2605.30189v1 Announce Type: cross Abstract: We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while pre

arXiv:2605.30011v1 Announce Type: cross Abstract: Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain

arXiv:2605.27466v1 Announce Type: cross Abstract: Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol t

arXiv:2605.28398v1 Announce Type: new Abstract: Hybrid-reasoning large language models (LLMs) expose explicit controls over reasoning effort, allowing users or systems to trade off answer quality agai

arXiv:2605.27722v1 Announce Type: new Abstract: Two-phase boiling enables heat transfer rates an order of magnitude higher than single-phase cooling, but it remains difficult to model due to the stron

arXiv:2605.28603v1 Announce Type: cross Abstract: Irregular multivariate time series forecasting is critical in many real-world applications, where time series are irregularly sampled and exhibit dyna

arXiv:2605.28360v1 Announce Type: new Abstract: Automatic prompt optimization (APO) has driven significant gains in LLM-based agentic workflows. However, existing methods treat each task's prompt as a

arXiv:2605.28557v1 Announce Type: cross Abstract: LLMs are increasingly used for software modernization, code translation, and database migration. However, LLM-based Oracle2PostgreSQL migration remain

arXiv:2605.28626v1 Announce Type: new Abstract: Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to th

arXiv:2605.26203v1 Announce Type: cross Abstract: The success of deployed agents relies on their ability to handle open-ended user requests using their inherent capabilities, not only in solving reque

arXiv:2605.27333v1 Announce Type: new Abstract: Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary

arXiv:2605.26902v1 Announce Type: cross Abstract: Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansi

arXiv:2605.06415v2 Announce Type: replace-cross Abstract: We introduce E = T*H/(O+B), a dimensionless control parameter that predicts whether Mixture-of-Experts (MoE) models will develop a healthy exp

arXiv:2605.24286v1 Announce Type: cross Abstract: Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produ

arXiv:2605.26112v1 Announce Type: new Abstract: This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and

arXiv:2605.25646v1 Announce Type: new Abstract: Autonomous ground robots operating in large-scale outdoor environments require both robust long-range navigation and fine-grained ''last-mile'' explorat

arXiv:2605.24699v1 Announce Type: new Abstract: Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet our results suggest that larger improvements can

arXiv:2605.24785v1 Announce Type: new Abstract: Recent advances in multimodal web agents often rely on increased inference-time computation, including rollout search, verifier passes, offline skill di

arXiv:2605.23258v1 Announce Type: new Abstract: KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or re

arXiv:2605.23078v1 Announce Type: cross Abstract: Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters.

arXiv:2605.23832v1 Announce Type: new Abstract: Deploying heterogeneous multi-agent robot fleets for collaborative perception requires robust data exchange and scalable software architectures. However

arXiv:2605.22222v1 Announce Type: new Abstract: Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a

arXiv:2506.21035v5 Announce Type: replace Abstract: Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based M

arXiv:2605.21958v1 Announce Type: new Abstract: When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Dia