Can AI Oversight Be Zero Knowledge?
arXiv:2610.01995v1 Announce Type: new Abstract: AI systems increasingly produce outputs from confidential data, such as a fitness-for-duty assessment from medical records or the predicted properties o
Knowledge catalogue
arXiv:2610.01995v1 Announce Type: new Abstract: AI systems increasingly produce outputs from confidential data, such as a fitness-for-duty assessment from medical records or the predicted properties o
arXiv:2602.18182v5 Announce Type: replace-cross Abstract: AI evaluation has primarily focused on measuring capabilities, with formal approaches inspired from Item Response Theory (IRT) being increasin
arXiv:2610.00238v1 Announce Type: cross Abstract: Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative
arXiv:2610.00197v1 Announce Type: new Abstract: We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches a
arXiv:2610.02019v1 Announce Type: cross Abstract: The rapid growth of video-based social media has increased users' exposure to harmful content, creating a need for reliable automated video safety det
arXiv:2610.00371v1 Announce Type: cross Abstract: Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creat
arXiv:2610.01133v1 Announce Type: cross Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield
arXiv:2610.01045v1 Announce Type: new Abstract: A chatbot that says 'I will remind you tomorrow' will not run again until the user writes. We call such a promise an empty commitment: a promise of an a
arXiv:2601.06701v2 Announce Type: replace-cross Abstract: Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Commo
arXiv:2610.02144v1 Announce Type: new Abstract: We introduce Faynt, a family of 10M- and 75M-parameter Transformer policies for Super Smash Bros. Melee, each controlling all 26 characters with a singl
arXiv:2610.01638v1 Announce Type: new Abstract: Federated learning (FL) on heterogeneous edge devices must jointly accommodate unequal resource budgets and domain-shifted local data. Existing resource
arXiv:2610.01939v1 Announce Type: new Abstract: Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observ
arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing
arXiv:2610.02140v1 Announce Type: cross Abstract: Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and re
arXiv:2610.01729v1 Announce Type: new Abstract: Algorithmic mathematical reasoning requires reliable decomposition, computation, and aggregation. Final-answer rewards provide limited guidance on inter
Whether you’re launching microservices in response to sudden traffic spikes, deploying new software releases, or scaling up application replicas, pod startup time is critical to maintaining a fast, re
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termin
arXiv:2610.02123v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale model capacity through sparse computation, routing each token through only a small subset of experts. In th
Hey local AI community, I've been working on this for a while and finally feel ok sharing it. It's a cyber benchmark where the model gets a shell in an isolated docker box and has to find the exact fl
Hi all! I am a former SWE who has recently transitioned into inference engineering. I launched a side hustle a few months back and I've just taken it full time due to excessive demand. Its been such a
arXiv:2602.20294v2 Announce Type: replace-cross Abstract: Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approac
Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI
arXiv:2610.01231v1 Announce Type: cross Abstract: Generative artificial intelligence has reduced the cost of producing plausible symbolic artefacts, leading recent organisation scholarship to identify
arXiv:2610.00353v1 Announce Type: new Abstract: A sound judgment applies the law to established facts and weighs the circumstances in which they arose. However, existing methods swing between rigid st
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source h
arXiv:2610.01172v1 Announce Type: new Abstract: We study learning rate (LR) scaling for hybrid architectures combining Transformer and State-Space Model (SSM) blocks, a class adopted by several recent
arXiv:2610.01800v1 Announce Type: new Abstract: Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural language. Supervis
arXiv:2610.01626v1 Announce Type: new Abstract: Action chunking improves the performance of policies learned by behavioural cloning, and several mechanisms have been proposed to explain why, including
arXiv:2610.00399v1 Announce Type: new Abstract: Metacognition involves reasoning about cognitive processes themselves. An example is in resource allocation where we choose how much time and effort to
arXiv:2610.01685v1 Announce Type: new Abstract: Constructive neural combinatorial optimization (NCO) has emerged as a promising paradigm that learns to construct solutions to combinatorial optimizatio
arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows t
arXiv:2610.01238v1 Announce Type: new Abstract: Unified language models are increasingly expected to combine heterogeneous capabilities, such as mathematics, code, instruction following, and controlla
arXiv:2610.00268v1 Announce Type: new Abstract: Multimodal graph learning faces a fundamental challenge: new classes may emerge after deployment, while models are trained with a fixed label space. Exi
arXiv:2610.01488v1 Announce Type: cross Abstract: Backchannel prediction has been studied almost entirely in dyadic conversation. We introduce a multi-party benchmark based on the AMI corpus, comprisi
https://www.percepta.ai/blog/can-llms-grow-their-own-capabilities https://www.percepta.ai/blog/spotlight-memory 'Our new architecture, Spotlight, replaces attention with a memory that escapes this tra
arXiv:2610.01787v1 Announce Type: new Abstract: Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies t
arXiv:2610.00445v1 Announce Type: new Abstract: Pairwise guide--transcript scores do not enforce conservation of a finite guide-loaded RISC pool when they are interpreted independently as occupancies.
I've been using my free time during weeknights and weekends for the last 11 months working on and refining a small domain-specific language model. It specializes on information about World War II. The
arXiv:2610.01601v1 Announce Type: cross Abstract: Decision models often score a variable-sized set of candidate actions encoded in a single sequence. This setting is increasingly relevant for System 1
arXiv:2610.00314v1 Announce Type: new Abstract: Research agents explain planned experiments. We measure predictive credit with paired forecasts sharing an intervention, forecaster, and outcome while v
arXiv:2610.01554v1 Announce Type: new Abstract: Wanda (Sun et al., 2024) prunes large language models by scoring weights independently within each linear projection, although queries and keys interact
arXiv:2508.08882v5 Announce Type: replace Abstract: Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-int
arXiv:2610.00940v1 Announce Type: cross Abstract: We propose ReHoPER, an inference-only, zero-shot method that improves large language models' reasoning by generating and answering intermediate questi
arXiv:2610.01222v1 Announce Type: new Abstract: As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their pro
arXiv:2610.00233v1 Announce Type: new Abstract: When an informed adversary shares the audience of a constrained signalling channel, the signal that best protects the truth is the signal that best desc
arXiv:2610.00715v1 Announce Type: new Abstract: Preference-based alignment methods typically optimize against a single preference model, and can therefore be brittle when pairwise preferences are unce
arXiv:2610.00797v1 Announce Type: new Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool cal
arXiv:2610.00531v1 Announce Type: new Abstract: AI-generated content, often called AI slop, is increasingly common everywhere, particularly in academia. Slop in AI-generated scientific papers, however
arXiv:2610.01278v1 Announce Type: new Abstract: Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors
arXiv:2610.01892v1 Announce Type: cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning t
arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving r
arXiv:2610.00417v1 Announce Type: new Abstract: Repeated training on model-generated data can degrade later models. One possible response is to use provenance when deciding which generated examples to
arXiv:2610.00910v1 Announce Type: cross Abstract: Human reasoning depends on how objects are related within propositions. extit{How do relations organize the language representations of contextual con
arXiv:2610.00835v1 Announce Type: new Abstract: Text-to-music generation models are trained on massive music collections, creating a growing need for data attribution methods that can quantify the con
arXiv:2610.01282v1 Announce Type: new Abstract: The rapid evolution of Intelligent Transportation Systems and Logistics (ITS&L) has become a cornerstone of the modern social economy, relying heavily o
arXiv:2610.00827v1 Announce Type: cross Abstract: Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one ans
arXiv:2610.01348v1 Announce Type: new Abstract: When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate
arXiv:2610.00666v1 Announce Type: cross Abstract: Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them.
arXiv:2610.00018v1 Announce Type: new Abstract: Role-specialized QA pipelines increasingly pass rationales from a reasoner to a verifier, but it is unclear what this message actually buys: better answ
arXiv:2610.01243v1 Announce Type: cross Abstract: Vision-language models (VLMs) increasingly act as judges that pick the best of several generated images, so their choices decide what users see. Such