Before any reviewer is assigned, a journal editor decides whether a manuscript merits external review. Yet this routine desk screening has no benchmark. We present PREREVIEWBENCH, the first controlled benchmark for journal desk screening. Because real desk decisions are confidential, we pair Web of Science papers published in 2025 with journals to construct proxy labels: true matches, within-field caliber surpluses and deficits, and cross-field scope mismatches. The 7,292 balanced paper–journal instances span four broad areas and 58 journals, supporting desk triage, branch-specific assessment (caliber fit or rejection cause), and transfer-journal recommendation. Evaluating four frontier LLM families, we find average triage accuracy of 0.965 on cross-field scope mismatches but only 0.572 on within-field caliber deficits, where blind expert-led review reproduces the triage labels perfectly. Transfer recommendation is weaker still, with the best Hit@1 at just 0.369. Models are also sensitive to input perturbations, and a cue suggesting that most papers merit review sharply shifts GPT-5.5’s decisions. These results point to a clear division of labor: LLMs can already carry the scope side of desk screening, while caliber judgment stays with editors. PREREVIEWBENCH makes that harder half measurable: whether an in-scope paper is strong enough for its journal.

The rapid growth of AI conference submissions is putting new pressure on peer review. AI reviewer systems are increasingly proposed as support, but prior work leaves unresolved what responsibility their outputs should carry when they can surface useful critiques yet remain risky as independent judgments. We frame this as a responsibility-boundary problem. Using 600 ICLR 2026 submissions, 2,231 human reviews, and 3,600 AI reviews, we operationalize this boundary through usable feedback, rating calibration, panel breadth, and grounded synthesis. AI can prepare critiques and organize evidence, while scoring, independent panel judgment, high-level synthesis, and final responsibility remain human-led. A GLM-5.2 validation on 100 NeurIPS 2022 papers with pre-ChatGPT reviews reproduces the workflow and calibration patterns. Motivated by this boundary, we develop Review Copilot, a workflow in which AI suggestions are inspected, edited, or rejected by human reviewers. In an initial controlled reviewer-in-the-loop study, Human+AI reviews improve actionability, evidence support, and professionalism relative to standalone baselines, while scores and recommendations remain human-authored. A user study of 275 reviewers across 411 papers further supports its practical usefulness. Together, these results support a review paradigm in which AI expands evidence-grounded critique while humans retain judgment, synthesis, and accountability.

This survey asks how far AI Scientist systems are from changing the world, and argues that their impact should be evaluated not by whether they produce plausible papers, but by whether they produce auditable research trajectories that can be inspected, reproduced, and challenged. We first provide a definition of AI Scientists, distinguish them from adjacent scientific AI systems, and organize the field around four core capabilities: knowledge acquisition, hypothesis generation, experimental validation, and evolution. We further synthesize representative systems by autonomy, execution grounding, auditability, human control, and evidence level. The resulting picture shows a field moving from prompt-to-paper automation toward auditable research laboratories, where executable grounding, provenance, and human-governed autonomy become central. We conclude by identifying open challenges toward trustworthy AI-driven science and providing a roadmap for integrating AI Scientists into the future landscape of scientific discovery.

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, the full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a live demo for easy access and interactive use at https://autofigure.cc/.

Temporal Knowledge Graphs (TKGs) incorporate the temporal feature to express the transience of knowledge by describing when facts occur. TKG extrapolation aims to infer possible future facts based on known history, which has garnered significant attention in recent years. Some existing methods treat TKG as a sequence of independent subgraphs to model temporal evolution patterns, demonstrating impressive reasoning performance. However, they still have limitations: 1) In modeling subgraph semantic evolution, they usually neglect the internal structural interactions between subgraphs, which are actually crucial for encoding TKGs. 2) They overlook the potential smooth features that do not lead to semantic changes, which should be distinguished from the semantic evolution process. Therefore, we propose Disentangled Multi-span Evolutionary Network (DiMNet) for TKG reasoning. Specifically, we design a multi-span evolution strategy that captures local neighbor features while perceiving historical neighbor semantic information, thus enabling internal interactions between subgraphs during the evolution process. To maximize the capture of semantic change patterns, we design a disentangle component that adaptively separates nodes’ active and stable features, used to dynamically control the influence of historical semantics on future evolution. Extensive experiments demonstrate that DiMNet achieves substantial performance in TKG reasoning, outperforming the state-of-the-art up to 22.7% in MRR.