arXiv preprints from January 1, 2026 through September 21, 2026 — 07:01:49 EST
Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prompt. A reliable critic could instead estimate token-level advantages from one response, but standard critic-based training recipes are often unstable. We study this instability and...
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. ReWorld separates the two during training and bounds them at inference. Mixed per-head attention windows confine most heads to...
Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at bug fixing, can they autonomously perform such migrations? Existing benchmarks cannot answer this question because they evaluate only behavioural...
Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial...
Discrete diffusion models offer a promising alternative to autoregressive generation by enabling parallel updates, but their sampling efficiency can depend strongly on the choice of the forward process and the sampler. For the uniform forward process, existing lower bounds for the standard $τ$-leaping sampler scale linearly with the...
Multi-vector retrieval has become a core primitive in semantic search applications that require fine-grained matching, such as information retrieval, recommender systems and bioinformatics. However, its high computational complexity and memory costs make low-latency retrieval difficult. Prior systems have attempted to optimize query...
Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for...
Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existing continuous frameworks still rely on decoders supervised with cross entropy (CE) because the flow trajectories are not guaranteed to terminate at valid token embeddings. Motivated by...
In CLAUDE.md, "do not" is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Both can express the same security goal, but they control the agent in different ways. We measure this gap in 481 public CLAUDE.md files. An LLM matched the...
Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views are sparse or target views lie far from the input. Recent work mitigates these artifacts using diffusion-based generative priors, but is specialized to...
Machine-learning-based anomaly detection is increasingly used in industrial control systems (ICS), yet most studies assume that detector training data is trustworthy. In practice, training data may be corrupted through compromised logs, labeling errors, manipulated historian records, or unsafe retraining processes. This paper...
While AI assistance can improve human task performance in the short term, it may also undermine the development of skills in the longer term. We examine this tension in a controlled logic-puzzle experiment involving on-demand AI assistance, where participants complete tasks before, during, and after AI is available. By experimentally...
Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly when data are scarce. We introduce Anatomy-Informed Neural Networks (AINN), in which soft anatomic priors enter as penalty terms in the loss (e.g., a branching penalty that treats a renal transplant artery off the iliac...
Accurate prediction of off-road vehicle motion over deformable terrain remains challenging because sinkage, slip, and traction vary with local soil conditions. Existing learning-based kinodynamic models directly approximate vehicle-terrain interactions from data but do not explicitly represent soil mechanics and offer limited physical...
Autonomous AI diagnostic agents, systems that analyse patient-specific clinical data and produce diagnostic outputs or triage decisions without mandatory real-time human review, are increasingly deployed across eHealth platforms in sub-Saharan Africa at a pace that has outrun the governance infrastructure needed to oversee them. While...
Users increasingly turn to large language models for emotional support, yet little is known about how these models actually conduct a psychotherapy interaction. We introduce an ontology of ten therapeutic moves: compact, function-based categories grounded in the MULTI-60 inventory, validated through an annotation campaign with five...
The rapid symptom change of Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) makes it critical to have time-sensitive prediction models. However, most current machine learning models studying AECOPD use clinical and laboratory data, which will inevitably cause latency. To ensure timely detection of AECOPD and...
We formalize the Steiner Traveling Salesman Problem (Steiner-TSP) on Graphs of Convex Sets (GCS), which seeks a minimum-cost closed trajectory through required convex sets while allowing optional transit vertices and revisits. To explore the resulting infinite solution space, we propose a unified branch-and-bound search over rooted...
The European Union (EU) has emerged as a leading regulatory body in the development of sustainability and privacy regulations. While new regulation requirements vary, many include a documentation artifact to ensure compliance. Notably, the Ecodesign for Sustainable Products Regulation (ESPR) introduces Digital Product Passports (DPPs)...
That a prompt's effect is not a property of the prompt is established: prompts optimised for one model degrade on another, and rankings reorder under neutral reformatting. That evidence is about task accuracy, which cannot say whether the interaction is a fact about task machinery or about the conditional distribution itself. We ask...
Due to their increasingly large volumes, outsourcing of trajectory storage and querying to third-party service providers has become attractive. However, in such outsourced environments, service providers may return incorrect, e.g., incomplete, tampered, or invalid query results, making verifiability of query results an important...
AI coding agents are increasingly integrated into software development workflows, operating on both sides of the pull-request (PR) process: AI authoring agents create or modify PRs, while AI reviewers evaluate them. This creates a closed loop in which one AI coding agent reviews a contribution attributed to another. We construct a...
Existing evaluations of automated root cause analysis (RCA) for microservices assess diagnostic performance mainly by endpoint correctness: whether a method localizes the responsible service. This criterion enables comparison but does not reveal the evidentiary basis of a diagnosis or the fault-propagation route connecting the source...
Test-Time Training (TTT) enables long-context processing via continuous weight updates during inference, but current methods struggle to balance the expressivity of per-token update dynamics with the hardware efficiency of chunk-wise approximations. We propose E$^2$-TTT (Expressive and Efficient TTT) to bridge this gap. Under the...
Studies of digital behavior often align users at moments they choose, such as opening an AI assistant, clicking a recommendation, or visiting a product page, and interpret higher activity afterward as an event effect. We show how this creates an endogenous time zero: the event occurs during an ongoing task episode, so the aligned...