CompanyAnthropic8 recent entries28 Sept 2026Analyzing and Mitigating Cost-Inefficient Behaviors in Coding AgentsarXiv:2609.30725v1 Announce Type: new Abstract: Although effective, coding agents often incur substantial monetary costs. Their recurring cost-inefficient behaviors remain underexplored. We conduct th→30 Sept 2026Koa-action: Fast and Consistent Structured Decision Making with Generative LLMsarXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic
CompanyOpenAI8 recent entries28 Sept 2026Muslim: A Deployed Arabic Voice AI Platform for Grounded Islamic KnowledgearXiv:2609.31511v1 Announce Type: new Abstract: We present Muslim, a production Arabic voice AI platform serving grounded, sourced Islamic knowledge to real users. Beyond a real-time voice pipeline (N→28 Sept 2026DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese EducationarXiv:2609.31568v1 Announce Type: new Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Clou→1 Oct 2026Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI InfrastructurearXiv:2609.38697v1 Announce Type: cross Abstract: We present Cascadia, a system for serving large language models on fleets of commodity Intel AIPCs using their CPU, integrated-GPU, and NPU resources.→2 Oct 2026Mean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incidentarXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' chara→5 Oct 2026IntentCoding: Amplifying User Intent in Code GenerationarXiv:2602.00066v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constrai→7 Oct 2026Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-TuningarXiv:2610.07385v1 Announce Type: new Abstract: Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never ac→7 Oct 2026Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code RenderingarXiv:2610.08137v1 Announce Type: cross Abstract: AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that are then rendered. These rout→9 Oct 2026From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security IncidentsarXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths
CompanyGoogle8 recent entries25 Sept 2026The Last Human Gate: Forward Deployed Engineering for Governance AutomationarXiv:2609.29345v1 Announce Type: new Abstract: Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human impleme→25 Sept 2026Robo-Harness K1: Harnessing Robot-Use Agents via Perception AugmentationarXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulat→28 Sept 2026StarWM: Self-Supervised Trained Attention Routing for Robust World ModelsarXiv:2609.30667v1 Announce Type: new Abstract: A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While rec→30 Sept 2026Neurosymbolic Routing for Reliable Reasoning on Resource-Constrained Edge DevicesarXiv:2609.35833v1 Announce Type: new Abstract: Running a language model on edge hardware provides private and low-latency reasoning without a network connection, and yet the small models that fit on →30 Sept 2026Koa-action: Fast and Consistent Structured Decision Making with Generative LLMsarXiv:2609.36115v1 Announce Type: new Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-critic→6 Oct 2026One Figure, Every Canvas: Editable Flowchart Relayout via Agentic PipelinearXiv:2610.06852v1 Announce Type: new Abstract: Pipeline figures in ML papers must be repurposed across many canvases, including paper columns, 16:9 slides, portrait posters, 1:1 social teasers, 9:16 →6 Oct 2026Dynamic Harness Search: Building Multi-Agent Systems Per-Query via PredictionarXiv:2610.04137v1 Announce Type: new Abstract: Agent harnesses specify the roles, instructions, tools, and communication structure used to solve a task, and the right harness depends on the query. Be→9 Oct 2026From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security IncidentsarXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths
CompanyMeta8 recent entries5 Oct 2026HazardWeaver: Scientific Route Selection for Hazard Analysis AgentsarXiv:2610.03591v1 Announce Type: new Abstract: Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large language models have spu→6 Oct 2026Homogeneous Semantic Alignment and Hierarchical Expert Routing for Radiology Report GenerationarXiv:2610.04499v1 Announce Type: new Abstract: Radiology report generation (RRG) aims to convert medical images into diagnostic texts to assist in clinical decision-making and alleviate the workload →6 Oct 2026DelegationBench: Measuring When AI Agents Should Ask Before ActingarXiv:2610.05532v1 Announce Type: cross Abstract: AI agents that send emails, edit files, and make purchases must decide when to act on their own and when to check with the user first. This decision i→7 Oct 2026Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model FamilyarXiv:2504.18225v2 Announce Type: replace Abstract: We introduce a new generation of small reasoning models for RAG, search, and source summarization. Pleias-RAG-350m and Pleias-RAG-1B are mid-trained→8 Oct 2026Bridge Routing Heads: Where Multilingual Multi-hop Reasoning Lives in LLMsarXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir→9 Oct 2026Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State QuantizationarXiv:2610.12444v1 Announce Type: new Abstract: Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent →12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still →12 Oct 2026Attention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsarXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d
CompanyMistral8 recent entries2 Sept 2026Beyond Scores: Understanding LLM-as-a-Judge Mechanisms in Summarization EvaluationarXiv:2609.01604v1 Announce Type: new Abstract: LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the intern→3 Sept 2026UTP-Bench: Uncertainty-aware Travel Planning BenchmarkarXiv:2609.02421v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planni→14 Sept 2026Dead Weights, Live Signals: Feedforward Graphs of Frozen Language ModelsarXiv:2604.08335v2 Announce Type: replace Abstract: We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through →22 Sept 2026Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV CachearXiv:2609.24635v1 Announce Type: new Abstract: When a language model reads an operation such as 'Swap the contents of Box F and Box B', its forward pass writes keys and values for those tokens into t→22 Sept 2026Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol StatesarXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i→24 Sept 2026Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMsarXiv:2609.27262v1 Announce Type: new Abstract: Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or →5 Oct 2026WakeKV: Reactive, Reversible KV Residency for Heads That Change Their MindsarXiv:2610.02713v1 Announce Type: new Abstract: Most KV-cache compression methods classify attention heads once, either offline or during prefill, and keep this classification fixed throughout generat→8 Oct 2026Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical InputsarXiv:2610.09033v1 Announce Type: new Abstract: Standard safety evaluations of large language models assess harmful requests written in canonical plain text, while models in real-world deployment rout
CompanyxAI8 recent entries27 Apr 2026Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes SettingsarXiv:2604.22662v1 Announce Type: cross Abstract: Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented landscape with little→10 Jul 2026SHAP-Weighted Cross-Modal Expert Fusion for Emotion and Sentiment Recognition: Evidence and LimitsarXiv:2607.08573v1 Announce Type: new Abstract: Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion,→27 Jul 2026Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-SciencearXiv:2607.22513v1 Announce Type: cross Abstract: Commercial large language models are increasingly used as knowledge references, yet their stance on contested scientific claims is neither stable nor →24 Aug 2026FlavourBench: Ranking Frontier Language Models with Executable Culinary Ground TrutharXiv:2608.20574v1 Announce Type: new Abstract: Open-ended language-model benchmarks usually inherit a judge: a human preference panel, another model, or a brittle exact-match key. We introduce Flavou→2 Sept 2026A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AIarXiv:2609.00572v1 Announce Type: cross Abstract: Enterprise artificial intelligence is increasingly embedded in decisions that must remain lawful, explainable, adaptable, and accountable despite pers→9 Sept 2026Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic PerspectivearXiv:2609.07213v1 Announce Type: cross Abstract: We observe a phenomenon that current algorithmic research in the field of explainable artificial intelligence primarily pursues better performance on →10 Sept 2026XAI-Refine: An Automated Explanation-Knowledge Loop for Brain-Age PredictionarXiv:2609.09388v1 Announce Type: new Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reprod→15 Sept 2026Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?arXiv:2609.14803v1 Announce Type: new Abstract: This paper reports experiments across six frontier model types from OpenAI, Anthropic, xAI, and Google DeepMind. Ten independent sessions per model type
CompanyDeepSeek8 recent entries2 Oct 2026On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and ConfidencearXiv:2610.00007v1 Announce Type: cross Abstract: Named-entity recognition (NER) is increasingly wanted on-device (no API, low latency, data kept local). The practitioner's question is not the leaderb→2 Oct 2026MoRA: MoE Pruning via Router Bias Learning and Expert ApproximationarXiv:2610.00367v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models enable parameter scaling with limited per-token computation by activating only a small subset of experts for each token,→6 Oct 2026CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE TrainingarXiv:2610.05744v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces →6 Oct 2026BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding ModelsarXiv:2610.06725v1 Announce Type: new Abstract: Mixture-of-experts (MoE) layers increase model capacity without a proportional increase in per-example computation. However, conventional flat routers c→7 Oct 2026SCOPE: Certified Theorem Proving with a Language Model as the Policy PlannerarXiv:2610.08319v1 Announce Type: new Abstract: In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails →8 Oct 2026EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional MemoryarXiv:2610.10533v1 Announce Type: new Abstract: Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language model→9 Oct 2026Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the WildarXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intell→12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still
CompanyNVIDIA8 recent entries29 Sept 2026Cache-Aware Conv3D Lowering Across Embedded World-Model DecodersarXiv:2609.31938v1 Announce Type: new Abstract: Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model b→30 Sept 2026ReCaVSR: One-Step Streaming Diffusion Video Super-Resolution with Recycled Latents and Learned Cache RoutingarXiv:2609.37831v1 Announce Type: new Abstract: Real-time diffusion-based video super-resolution (VSR) is in high demand for online streaming, yet stringent latency requirements often compromise gener→30 Sept 2026Mixture-of-Kittens: MoE Megakernel for NVL72sarXiv:2609.36070v1 Announce Type: cross Abstract: AI accelerator systems are rapidly consolidating into scale-up architectures, where tens to thousands of GPUs communicate over high-bandwidth, single-→2 Oct 2026Fast Polynomial Transcendentals for LLMsarXiv:2610.00049v1 Announce Type: new Abstract: Graphics processing unit (GPU) generations scale matrix, special-function, and memory pipelines at different rates, so kernel bottlenecks move as hardwa→5 Oct 2026Query-aware routing for Cross-lingual performance gains in EncodersarXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language→9 Oct 2026DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert CompositionarXiv:2610.11317v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with recent work demonstrating the benefits of fine-grai→12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still →12 Oct 2026RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language ModelsarXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the add