1391 matching published research entries
Artificial Intelligence · 2026-11-05
arXiv:2611.05620v1 Announce Type: new Abstract: On Replit, our agentic engineering platform, users now build entire products without writing code, through successive feature requests to an agent. Yet existing coding benchmarks evaluate single, fully specified tasks, and many are near saturation. We introduce ViBench 2.0, a benchmark for long-horizon software building that we use to select our platform's models.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05611v1 Announce Type: new Abstract: Speculative decoding (SD) speeds up large language model (LLM) serving, but its gain depends on the workload's \emph{shape}, such as batch size and context length, and on its \emph{content}.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05590v1 Announce Type: new Abstract: What should ``verified'' mean when evaluating LLM-generated code? Many existing pipelines report a single verification number. We argue this collapses three distinct properties measured in a conditional audit sequence: verifier acceptance (Surface A), \emph{syntactic specification binding (Surface B: does the proof obligation bind to the spec?), and \emph{semantic…
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05586v1 Announce Type: new Abstract: As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge. Existing reputation systems depend on scarce resources like human curation, identity credentials, or voluntary reviews, while naive volume rankings are vulnerable to Sybil attacks.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05581v1 Announce Type: new Abstract: Real-world vision is dynamic and scene-rich, while EEG and fMRI resolve it at complementary temporal and spatial scales. Most neural decoding systems, however, align one modality in isolation and mostly against static images or short clips.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05556v1 Announce Type: new Abstract: LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled sets that validate them hold a few hundred items or fewer.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05551v1 Announce Type: new Abstract: Virtual trials use routinely collected clinical data to evaluate treatment strategies, but translating a study protocol into an executable analysis requires determining how clinical concepts and study requirements should be represented in the available data and applied consistently across the workflow.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05549v1 Announce Type: new Abstract: Transparency has become a central principle in AI governance, yet there is little agreement about what transparency means, for whom, and in what contexts. Drawing on interpretive flexibility within the Social Construction of Technology, this paper examines how different stakeholders understand and experience transparency in generative AI.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05548v1 Announce Type: new Abstract: We evaluate the extent to which agentic AI models can complete an end-to-end data science project, and how this improves with feedback. A 'writer' model with specific tools creates a complete data science project including downloading, cleaning, and analyzing a dataset, and writing a short paper about it. The project is executed and a 'grader' model evaluates it.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05542v1 Announce Type: new Abstract: Whole-page ranking jointly optimizes advertisements and organic content to balance business outcomes and user engagement under complex layout and business constraints. Existing non-autoregressive (NAR) approaches enable efficient page generation but typically score candidate items independently of previously selected items, limiting their ability to capture…
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05524v1 Announce Type: new Abstract: We propose MA-SafeDiffuser, a multi-agent extension of SafeDiffuser that equips diffusion-based trajectory planners with finite-time diffusion invariance guarantees for joint-agent safety specifications.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05512v1 Announce Type: new Abstract: AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons. Yet existing benchmarks fall short of real knowledge work: many rely on synthetic data or isolated tasks, missing the complex, multi-party dynamics of collaborative projects, where critical information is scattered across…
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05459v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: finding relevant articles, interpreting them, synthesizing across them, and proposing future research.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05450v1 Announce Type: new Abstract: As agents become more capable, they are moving beyond one-off tasks toward sustained assistance across successive user goals. Such assistance requires agents to discover how unfamiliar environments work, reuse what they learn across tasks, and keep that experience current as environments evolve.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05394v1 Announce Type: new Abstract: Tiered inference distributes large language model computation across a hierarchy of devices, from on-device and edge hardware to the datacenter, and is increasingly offered as the route to cheaper, lower-latency, and more private serving.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05393v1 Announce Type: new Abstract: Large language models perform strongly on standard medical QA but degrade on harder reasoning tasks, where multi-agent debate often fails to beat strong single-model prompting. We argue that a key limitation is that existing systems select experts and retrieve knowledge from the question alone, rather than from gaps that emerge during reasoning.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05392v1 Announce Type: new Abstract: Agentic artificial intelligence (AI) systems powered by large language models (LLMs) execute as autonomous multi-step pipelines that dynamically invoke tools, integrate observations into memory, and iterate until a task is resolved or a resource budget is exhausted.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05391v1 Announce Type: new Abstract: Tool descriptions tell an agent what an action can do, but they do not necessarily reveal whether that action is healthy or suitable at the moment of use. Execution harnesses often possess this information through monitors, traces, and recent failures while the model choosing the next action does not. We call this gap operational blindness.
arXiv AIRead article →Artificial Intelligence · 2026-11-05
arXiv:2611.05390v1 Announce Type: new Abstract: Multi-agent language-model systems often add a reviewer to improve an upstream agent's decision. Yet a reviewer can both repair errors and replace decisions that were already correct. We study this as a problem of institutional jurisdiction: conditional on the same proposal, task information, model, and review output, when is the reviewer authorized to make its…
arXiv AIRead article →Science · 2026-11-05
During England's Industrial Revolution, when the country's farming-based economy transformed into an industrial one between roughly 1760 and 1840, pollution, harsh working conditions, inadequate housing and limited access to sunlight drove disease. Rickets, in which the growing skeleton fails to properly mineralize, was commonplace among children.
Phys.org ResearchRead article →Artificial Intelligence · 2026-11-05
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
MIT Artificial IntelligenceRead article →Science · 2026-11-05
British pubs are disappearing at an alarming rate. Last year, around eight closed down every week.
Phys.org ResearchRead article →Science · 2026-11-05
People living with ALS and their families in Japan are eager to help shape research on the disease, even though most have never heard of patient and public involvement (PPI), according to a study published on Oct. 30, 2026, in Research Involvement and Engagement.
Phys.org ResearchRead article →Space & Discovery · 2026-11-05
On Wednesday, NASA unveiled its newest experimental aircraft, the X-70 Fractal, during the UP.Summit at the agency’s Kennedy Space Center in Florida. This high-performance, highly adaptable research platform is designed to accelerate the development and testing of advanced aviation technologies. The crewed X-70 features advanced, rapidly reconfigurable flight-control technology that will allow NASA to explore […]
NASARead article →