Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2610.06977v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-sou...
arXiv:2610.06993v1 Announce Type: cross Abstract: Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However,...
arXiv:2610.06996v1 Announce Type: cross Abstract: Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memor...
arXiv:2610.07062v1 Announce Type: cross Abstract: Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these response...
arXiv:2610.07098v1 Announce Type: cross Abstract: Large transformer-based models increasingly depend on multi-GPU execution, which requires frequent collective communication among GPUs. Existing comm...
arXiv:2610.07115v1 Announce Type: cross Abstract: The order in which candidate responses are presented can change an LLM judge's verdict. Detecting such a position flip ordinarily requires judging ea...
PlaySuite is a large-scale benchmark that evaluates interactive visual intelligence by using over 5,000 open-source video games from platforms like PyWeek and itch.io. The benchmark covers diverse game engines (Pygame, HTML5, Godot, Unity) and introduces a unified closed-loop interaction framework and a Video-LLM-as-a-judge protocol to standardize progress measurement. Evaluation of fourteen recent models shows a perception-action gap, with strong reasoning but poor sustained progress, spatial grounding, action execution, and self-correction.
The paper introduces TraceDSE, an agentic design space exploration framework for jointly mapping AI inference workloads to heterogeneous edge SoCs and configuring each processing unit. Unlike traditional black-box optimization, TraceDSE uses a proposer‑critic loop powered by large language models and enriched with system execution traces to identify bottlenecks and refine design choices. Experiments on an Intel Meteor Lake SoC show that TraceDSE outperforms state‑of‑the‑art evolutionary and Bayesian methods, improving Pareto frontier hypervolume by up to 68% while reducing hardware evaluations by 6–9×.
arXiv:2610.07207v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creates a hidden reliability probl...
arXiv:2610.07224v1 Announce Type: cross Abstract: Clinical notes capture most of what is documented about a patient's care, but they cannot be used for research until protected health information (PH...
The paper proposes the Analytical Memory Unit (AMU), a memory schema that attaches a full derivation (lineage) graph to every cached result in enterprise AI agents. By gating retrieval with a policy that requires authorization for every column touched, the authors prove that sensitive columns cannot be leaked through derived results, achieving up to 90% lineage completeness to eliminate leakage. Experiments show lineage‑gated retrieval removes 18.8‑25.5% of cross‑department leakage while maintaining 81.5‑82.6% memory reuse with minimal overhead, and a real‑agent proof‑of‑concept demonstrates zero leaks over multiple interactions.
arXiv:2610.07276v1 Announce Type: cross Abstract: Deployment-time safety of language models is commonly implemented through runtime guardrails such as input moderation, routing, retrieval verificatio...
The paper introduces FlowAgent, an AI agent deployed at Google to automatically repair test failures in the pre-submit continuous integration workflow. FlowAgent uses a ReAct-style generate-and-validate loop with strict latency and quality filters, and was evaluated on 195 real-world failures with a 67.18% accuracy rate. After deployment, it suggested fixes on 295,508 changes, with developers previewing 65,069 and applying 28,554, and received positive feedback from interviews.
arXiv:2610.07298v1 Announce Type: cross Abstract: Cyber threat analysis increasingly depends on evidence distributed across vendor advisories, vulnerability databases, and threat intelligence sources...
arXiv:2610.07335v1 Announce Type: cross Abstract: Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous a...
arXiv:2610.07339v1 Announce Type: cross Abstract: Tactical Combat Casualty Care (TC3) requires responders to connect visual observations of injuries and interventions with established clinical guidan...
The paper introduces SEMAADB, a dataset comprising 3,000 engineering contexts and 15,000 SysML diagrams, each context containing five interconnected views (Requirement, Block Definition, Activity, State Machine, and Sequence). The authors verified diagram consistency and created a 100-context human‑verified benchmark. They evaluated three language models on diagram repair and cross‑diagram update tasks, finding that while syntax repair is largely solved, semantic repair and cross‑diagram consistency remain challenging.
arXiv:2610.07457v1 Announce Type: cross Abstract: Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GP...
arXiv:2610.07460v1 Announce Type: cross Abstract: Inserting objects into existing 3D scenes requires more than selecting a plausible location: the inserted object must also fit local geometry while...
arXiv:2610.07532v1 Announce Type: cross Abstract: LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks inc...