arXiv:2604.04373v1 Announce Type: new Abstract: There is growing interest in improving LLMs without updating model parameters. One well-established direction is test-time scaling, where increased inference-time computation (e.g., longer reasoning, sampling, or search) is used to improve performance. However, for complex reasoning and agentic tasks, naively scaling test-time compute can substantially increase cost and still lead to wasted budget on suboptimal exploration. In this paper, we explore \emph{context} as a complementary scaling axis for improving LLM performance, and systematically study how to construct better inputs that guide reasoning through \emph{experience}. We show that effective context construction critically depends on \emph{decocted experience}. We present a detailed analysis of experience-augmented agents, studying how to derive context from experience, how performance scales with accumulated experience, what characterizes good context, and which data structures best support context construction. We identify \emph{decocted experience} as a key mechanism for effective context construction: extracting essence from experience, organizing it coherently, and retrieving salient information to build effective context. We validate our findings across reasoning and agentic tasks, including math reasoning, web browsing, and software engineering.

arXiv:2604.03304v1 Announce Type: cross Abstract: The discovery of new energetic materials remains a pressing challenge hindered by limited availability of high-quality data. To address this, we have developed generative molecular language models that have been pretrained on extensive chemical data and then fine-tuned with curated energetic materials datasets. This transfer-learning strategy extends the chemical language model capabilities beyond the pharmacological space in which they have been predominantly developed, offering a framework applicable to other data-spare discovery problems. Furthermore, we discuss the benefits of fragment-based molecular encodings for chemical language models, in particular in constructing synthetically accessible structures. Together, these advances provide a foundation for accelerating the design of next-generation energetic materials with demanding performance requirements.

arXiv:2604.03782v1 Announce Type: cross Abstract: We analyze the last-iterate convergence of the Anchored Gradient Descent Ascent algorithm for smooth convex-concave min-max problems. While previous work established a last-iterate rate of $\mathcal{O}(1/t^{2-2p})$ for the squared gradient norm, where $p \in (1/2, 1)$, it remained an open problem whether the improved exact $\mathcal{O}(1/t)$ rate is achievable. In this work, we resolve this question in the affirmative. This result was discovered autonomously by an AI system capable of writing formal proofs in Lean. The Lean proof can be accessed at https://github.com/google-deepmind/formal-conjectures/pull/3675/commits/a13226b49fd3b897f4c409194f3bcbeb96a08515

arXiv:2604.04334v1 Announce Type: cross Abstract: Researchers and practitioners are increasingly considering reinforcement learning to optimize decisions in complex domains like robotics and healthcare. To date, these efforts have largely utilized expectation-based learning. However, relying on expectation-focused objectives may be insufficient for making consistent decisions in highly uncertain situations involving multiple heterogeneous groups. While distributional reinforcement learning algorithms have been introduced to model the full distributions of outcomes, they can yield large discrepancies in realized benefits among comparable agents. This challenge is particularly acute in healthcare settings, where physicians (controllers) must manage multiple patients (subordinate agents) with uncertain disease progression and heterogeneous treatment responses. We propose a Boosted Distributional Reinforcement Learning (BDRL) algorithm that optimizes agent-specific outcome distributions while enforcing comparability among similar agents and analyze its convergence. To further stabilize learning, we incorporate a post-update projection step formulated as a constrained convex optimization problem, which efficiently aligns individual outcomes with a high-performing reference within a specified tolerance. We apply our algorithm to manage hypertension in a large subset of the US adult population by categorizing individuals into cardiovascular disease risk groups. Our approach modifies treatment plans for median and vulnerable patients by mimicking the behavior of high-performing references in each risk group. Furthermore, we find that BDRL improves the number and consistency of quality-adjusted life years compared with reinforcement learning baselines.

arXiv:2502.08547v2 Announce Type: replace Abstract: The widespread adoption of electronic health records has created new opportunities for translational clinical research, yet this promise remains constrained by fragmented data across privacy-siloed institutions and substantial heterogeneity in local coding practices. While privacy-preserving collaborative learning allows institutions to work together without sharing patient-level data, it does not address inconsistencies in how clinical concepts are represented across sites. We introduce a graph-based framework that addresses this gap by treating data harmonization as a scalable representation learning problem. Rather than relying on fixed standards or manual mappings, the framework integrates institution-specific summary statistics from health records, curated biomedical knowledge graphs, and semantic information derived from large language models to learn a shared semantic space. This joint learning approach aligns diverse, site-specific vocabularies while preserving patient privacy. Evaluated across seven institutions and two languages, the framework provides a robust, data-centric foundation for training and deploying clinical models across heterogeneous healthcare systems.

arXiv:2503.11572v4 Announce Type: replace-cross Abstract: Implicit biases refer to automatic mental processes that shape perceptions, judgments, and behaviors. Previous research on "implicit bias" in LLMs focused primarily on outputs rather than the processes underlying the outputs. We present the Reasoning Model Implicit Association Test (RM-IAT) to study implicit bias-like processing in reasoning models, LLMs that use step-by-step reasoning to solve complex tasks. Using RM-IAT, we find that reasoning models like o3-mini, DeepSeek-R1, gpt-oss-20b, and Qwen-3 8B consistently expend more reasoning tokens on association-incompatible tasks than association-compatible tasks, suggesting greater computational effort when processing counter-stereotypical information. Conversely, Claude 3.7 Sonnet exhibited reversed patterns, which thematic analysis associated with its unique internal focus on reasoning about bias and stereotypes. These findings demonstrate that reasoning models exhibit distinct implicit bias-like patterns and that these patterns vary significantly depending on the models' internal reasoning content.

arXiv:2601.11109v3 Announce Type: replace-cross Abstract: Vision-as-inverse-graphics, the concept of reconstructing images into editable programs, remains challenging for Vision-Language Models (VLMs), which inherently lack fine-grained spatial grounding in one-shot settings. To address this, we introduce VIGA (Vision-as-Inverse-Graphics Agent), an interleaved multimodal reasoning framework where symbolic logic and visual perception actively cross-verify each other. VIGA operates through a tightly coupled code-render-inspect loop: synthesizing symbolic programs, projecting them into visual states, and inspecting discrepancies to guide iterative edits. Equipped with high-level semantic skills and an evolving multimodal memory, VIGA sustains evidence-based modifications over long horizons. This training-free, task-agnostic framework seamlessly supports 2D document generation, 3D reconstruction, multi-step 3D editing, and 4D physical interaction. Finally, we introduce BlenderBench, a challenging visual-to-code benchmark. Empirically, VIGA substantially improves accuracy compared with one-shot baselines in BlenderGym (35.32%), SlideBench (117.17%) and our proposed BlenderBench (124.70%).

arXiv:2603.13285v2 Announce Type: replace-cross Abstract: Existing evaluation methods largely rely on clean, static benchmarks, which can overestimate true model performance by failing to capture the noise and variability inherent in real-world user inputs. This is especially true for language models, which can face human-generated text queries containing mistakes, typos, or alternative ways of phrasing the same question. In this work, we introduce a theoretical framework for quantifying model sensitivity to prompt variants, or brittleness, that can enable us to disentangle data-induced difficulty from prompt-related variability. Using this framework, we design a novel evaluation pipeline, Brittlebench, to holistically evaluate the sensitivity of frontier models. We apply semantics-preserving perturbations to a suite of popular benchmarks, and observe model performance to degrade as much as 12%. However, these perturbations do not affect all models equally: even a single perturbation alters the relative ranking of models in 63% of cases, impacting conclusions about comparative model performance. Decomposing the total variance of both state-of-the-art open-weight and commercial models, we find that semantics-preserving input perturbations can account for up to half of the performance variance for a given model. Brittlebench highlights the need for more robust evaluations and models, and allows us to systematically understand model brittleness.

Nature Medicine, Published online: 07 April 2026; doi:10.1038/s41591-026-04307-8

In a phase 1 basket trial, the small interfering RNA zodasiran, targeting ANGPTL3, lowered triglycerides in patients with severe hypertriglyceridemia and lowered both triglycerides and low-density lipoprotein cholesterol in patients with heterozygous familial hypercholesterolemia.

Nature Medicine, Published online: 06 April 2026; doi:10.1038/s41591-026-04282-0

In the phase 3 EMN24 IsKia trial, transplant-eligible patients with newly diagnosed multiple myeloma who received isatuximab with carfilzomib, lenalidomide and dexamethasone pretransplant induction and post-transplant consolidation showed higher rates of measurable residual disease negativity after consolidation than patients who received carfilzomib, lenalidomide and dexamethasone.

Nature Medicine, Published online: 06 April 2026; doi:10.1038/s41591-026-04287-9

Analysis of neuroimaging datasets across five major psychedelics revealed a shared brain signature and provides a comprehensive insight into how these drugs reorganize brain architecture.

npj Digital Medicine, Published online: 06 April 2026; doi:10.1038/s41746-026-02600-x

Towards a physics informed digital twin to predict cerebral blood flow and cerebral vascular regulation

Nature, Published online: 06 April 2026; doi:10.1038/d41586-026-01027-4

A goal-driven approach to medical research and development in the United States would address unmet medical needs, reduce costs and improve the reach of treatments.

arXiv:2604.01452v1 Announce Type: new Abstract: Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.

arXiv:2604.01461v1 Announce Type: new Abstract: Reducing hallucinations in Large Language Models (LLMs) is essential for improving the accuracy of data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents but fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), a novel approach that uses the relationships between documents to improve extraction accuracy. Our application domain is in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. High-confidence results, supported by peer validation, are considered reliable. Our experiments demonstrate up to 98% precision in outlier detection across 6 domains of science, demonstrating that our design reduces hallucinations, enhances trust in automated systems, and allows researchers to focus on ambiguous cases, streamlining the data extraction workflows.

arXiv:2604.02259v1 Announce Type: cross Abstract: To harness the power of Language Models in answering domain specific specialized technical questions, Retrieval Augmented Generation (RAG) is been used widely. In this work, we have developed a Q\&A application inspired by the Retrieval Augmented Generation (RAG), which is comprised of an in-house database indexed on the arXiv articles related to the Electron-Ion Collider (EIC) experiment - one of the largest international scientific collaboration and incorporated an open-source LLaMA model for answer generation. This is an extension to it's proceeding application built on proprietary model and Cloud-hosted external knowledge-base for the EIC experiment. This locally-deployed RAG-system offers a cost-effective, resource-constraint alternative solution to build a RAG-assisted Q\&A application on answering domain-specific queries in the field of experimental nuclear physics. This set-up facilitates data-privacy, avoids sending any pre-publication scientific data and information to public domain. Future improvement will expand the knowledge base to encompass heterogeneous EIC-related publications and reports and upgrade the application pipeline orchestration to the LangGraph framework.

arXiv:2510.13714v3 Announce Type: replace-cross Abstract: Video comprises the vast majority of bits that are generated daily, and is the primary signal driving current innovations in robotics, remote sensing, and wearable technology. Yet, the most powerful video understanding models are too expensive for the resource-constrained platforms used in these applications. One approach is to offload inference to the cloud; this gives access to GPUs capable of processing high-resolution videos in real time. But even with reliable, high-bandwidth communication channels, the combined latency of video encoding, model inference, and round-trip communication prohibits use for certain real-time applications. The alternative is to use fully local inference; but this places extreme constraints on computational and power costs, requiring smaller models and lower resolution, leading to degraded accuracy. To address these challenges, we propose Dedelayed, a real-time inference system that divides computation between a remote model operating on delayed video frames and a local model with access to the current frame. The remote model is trained to make predictions on anticipated future frames, which the local model incorporates into its prediction for the current frame. The local and remote models are jointly optimized with an autoencoder that limits the transmission bitrate required by the available downlink communication channel. We evaluate Dedelayed on the task of real-time streaming video segmentation using the BDD100k driving dataset. For a round trip delay of 100 ms, Dedelayed improves performance by 6.4 mIoU compared to fully local inference and 9.8 mIoU compared to remote inference -- an equivalent improvement to using a model ten times larger. We release our training code, pretrained models, and python library at https://github.com/InterDigitalInc/dedelayed .

arXiv:2603.26203v2 Announce Type: replace-cross Abstract: Technology change happens quickly such that new trends tend to crowd out the focus on what was new just yesterday. In this paper the peak popularity of the confluence of Object Technologies with early Web adoption is explored through the content of a seminar held in 1999. Distributed architectures were undergoing significant change at this point, and deeper software capabilities were just beginning to be broadly accessible over the Internet. The Object Web arose and was infused with new development tools reflecting these capabilities and allowing design of applications for deployment during the early days of the World Wide Web. This conference discussed the history, evolution, and use of these tools, architectures, and their future possibilities. The continued dominance of these approaches although under different names is demonstrated even though the term Object Web has receded in use. Favored newer offerings such as Kubernetes and microservices still model the core design attributes of the Object Web for example. Aside from connecting this seminar to relevance in the software world of today this paper also touches on the early AI tools demonstrated in this seminar a quarter century ago and how the popularity wave of any given technology might affect the current focus on AI technology offerings.

Nature Medicine, Published online: 03 April 2026; doi:10.1038/s41591-026-04305-w

To accelerate therapeutic development and equip stakeholders with clear benchmarks, the authors outline target product profiles for therapies designed to delay or prevent the onset of clinical symptoms of Alzheimer’s disease.

Nature Cancer, Published online: 03 April 2026; doi:10.1038/s43018-026-01142-1

Izar and colleagues review the insights into cancer biology gained via single-cell analyses and spatial profiling and overview the challenges and opportunities associated with the implementation of these approaches to guide clinical discovery.