Artificial Intelligence Papers of the Week

On downstream accuracy evaluations, these predictions fail when the weaker models produced by the cheaper runs score near zero accuracy, because these scores give no trend to extrapolate to larger scales. We introduce hinted scaling laws, which use privileged information to turn a benchmark into a continuum of easier versions so that even the small models score above zero.

We present Pixel, a co-designed full-stack system for learning general-purpose mobile manipulation.

Through frequent compaction, we show across a broad range of long-horizon and long-input tasks that frontier language models sacrifice little to no task accuracy when maintaining short contexts.

Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework.

We introduce ID-WM (Implicit Dynamics World Models), a hierarchical world model that decouples state-space reachability from local control.

We present SwarmEvolve, a framework in which hundreds of low-cost agents per round work in swarms, reason in latent space without decoding to text, and share information by passing KV caches.

We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback.

We present Pixel-UMI, a pipeline for learning environment-aware whole-body policies from human data.

Beyond surveying existing methods, we propose a unified framework for evaluating mechanistic interpretability claims and characterise six research orientations by their goals, assumptions, and trade-offs.

These tests score individual answers, but reveal less about whether a model can integrate subspecialty knowledge with multimodal evidence and track a patient's condition throughout a course of care. To close this gap, we introduce NPCBench, a clinical apprenticeship benchmark for nasopharyngeal carcinoma (NPC).

We introduce DreamX, which repurposes a pretrained video diffusion model as a universal latent action learner.

With the world as an evaluation, we found that frontier AI-Scientists can already surpass the human researchers 74% of the time.

We show that harness design can be automated, offering a strong alternative to finetuning on a novel setup.

We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis.

Importance weighting cuts this loop only while the lag ratio stays concentrated, and on Qwen3-1.7B it fails at the step where the effective sample size of the ratio falls below one half. From this account we derive the \textbf{discrepancy-lag correction} (DLC), which centers the numerical discrepancy, clips the lag ratio against the sampler's weights and resynchronizes the sampler when this effective sample size falls below one half.

Other artifacts--ontology, graph, wiki, timeline, mind map, memory--pay off in deployment (governance, integration, onboarding, temporal orientation, continuity) where accuracy benchmarks cannot see them. We describe RAGFlow's pipeline and harness (open source at this https URL), which turns the loop into five disciplined stations and keeps the context entering the model the smallest sufficient set; together they form an agent-native database: a store that hands the agent compiled, governed context instead of a ranked list of passages.

We propose LoCo, a local preference learning method for reasoning compression.

In this paper, we derive an asymptotically subquadratic sparse attention method based on a hierarchical, tree-structured indexer, which we call Zyphra Hierarchical Attention (ZHA).

We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics.

The model performs accurate local calculations: batch-normalization statistics lead it to infer about three optimizer steps on networks stopped after three updates, and output-layer sign patterns recover the vehicle/animal split of CIFAR-10.