AAblation Study1 We conduct ablation studies to evaluate three key design choices in PosterAgent: (1) the binary-tree2 layout strategy for layout planning; (2) the inclusion of a commenter module as a visual critic; and3 (3) the use of in-context examples to enhance the visual perception capabilities of the commenter.4 We define the following variants:5 Direct: replacing the binary-tree layout with direct layout generation by an LLM;6 Tree: using the binary-tree layout strategy but removing the commenter module;7 Tree + Commenter: including the commenter module but without in-context examples;8 Tree + Commenter + IC: the full system, with both the commenter and in-context examples.9 All ablation variants are implemented using PosterAgent-4o, keeping all other components un-10 changed to isolate the effect of each factor. We visualize and compare results across five randomly11 selected papers from Paper2Poster, as shown in Figures 1 to 5.12 When prompting the LLM to directly generate poster layouts (Direct), the results are often structurally13 compromised (e.g., Figures 1a-3a), or resemble blog-style layouts that lack visual hierarchy and14 appeal (Figures 4a,5a). Fine-grained layout components, such as text boxes and figures, are especially15 challenging to synthesize in this setting: for instance, Figures1a-4a exhibit missing text boxes that16 leave noticeable blank areas, and Figure 4a fails to preserve the correct aspect ratio of figures.17

Vision-language models (VLMs) excel at descriptive tasks, but whether they truly understand scenes from visual observations remains uncertain. We introduce IR3DBench, a benchmark challenging VLMs to demonstrate understanding through active creation rather than passive recognition. Grounded in the analysis-bysynthesis paradigm, IR3D-Bench tasks Vision-Language Agents (VLAs) with actively using programming and rendering tools to recreate the underlying 3D structure of an input image, achieving agentic inverse rendering through tool use. This "understanding-by-creating" approach probes the tool-using generative capacity of VLAs, moving beyond the descriptive or conversational capacity measured by traditional scene understanding benchmarks. We provide a comprehensive suite of metrics to evaluate geometric accuracy, spatial relations, appearance attributes, and overall plausibility. Initial experiments on agentic inverse rendering powered by various state-of-the-art VLMs highlight current limitations, particularly in visual precision rather than basic tool usage. IR3D-Bench, including data and evaluation protocols, is released to facilitate systematic study and development of tool-using VLAs towards genuine scene understanding by creating.

Users can drag-and-drop files to start creating a Croissant dataset.

A sitting is a meeting of parliament members. While in the virtual environment, you will need to install the specific Gensim1 version needed for theCompassapproach. Inotherinstances,thebeginning of the line that specifies the speaker consists of the role of the parliament member, for example "SPEAKEROFTHEPARLIAMENT" (meaning the member of parliament presiding), followed, but not always, by the actual full name of the person in parenthesis. Theidisa unique number we assigned to each file. Themainchallenge of translating the files from Greek to English was the conversion of the Greek alphabetic numeralstoindo-arabicnumerals.

For VaTeX captioning and retrieval, we use the latest v1.1 version3, which contains 25,991 videos for training and 6,000 videos for public testing. The statistics can be found in Table 1. Visual genome synsets are pairs, where the keys are noisy natural language phrases and the values are the mapped WordNet synsets [6]. Ifavisualtokenoccurs in multiple frames, we use the averaged frame indexas its temporal indicator. Specifically,for UniVL, we set the number of epoches to be50 and the linear warmup steps to be40.

Scientific reasoning through Large Language Models in heliophysics involves more than just recalling facts: it requires incorporating physical assumptions, maintaining consistent units, and providing clear scientific formats through coordinated approaches. To address these challenges, we present Reasoning With a Star, a newly contributed heliophysics dataset applicable to reasoning; we also provide an initial benchmarking approach. Our data are constructed from National Aeronautics and Space Administration & University Corporation for Atmospheric Research Living With a Star summer school problem sets and compiled into a readily consumable question-and-answer structure with question contexts, reasoning steps, expected answer type, ground-truth targets, format hints, and metadata. A programmatic grader checks the predictions using unit-aware numerical tolerance, symbolic equivalence, and schema validation. We benchmark a single-shot baseline and four multi-agent patterns, finding that decomposing workflows through systems engineering principles outperforms direct prompting on problems requiring deductive reasoning rather than pure inductive recall.

Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion. Numerous methods and tools exist for each of these tasks, but support for combining them into reproducible and effective end-to-end pipelines is still lacking. We present a new framework, KGpipe for defining and executing integration pipelines that can combine existing tools or LLM (Large Language Model) functionality. To evaluate different pipelines and the resulting KGs, we propose a benchmark to integrate heterogeneous data of different formats (RDF, JSON, text) into a seed KG. We demonstrate the flexibility of KGpipe by running and comparatively evaluating several pipelines integrating sources of the same or different formats using selected performance and quality metrics.

Function calling (FC) empowers large language models (LLMs) and autonomous agents to interface with external tools, a critical capability for solving complex, real-world problems. As this ability becomes increasingly central to advanced AI systems, the need for high-quality, multi-turn training data to develop and refine it cannot be overstated. Existing data synthesis methods, such as random environment sampling or multi-agent role-playing, are not powerful enough to generate high-quality data in real-world environments. Practical challenges come in three folds: targeted data synthesis, hard query construction, and multi-turn logical dependency. To address these structural deficiencies, we present FunReason-MT, a novel data synthesis framework for real-world multi-turn tool use. FunReason-MT resolves the complexity barrier in multi-turn FC data by employing 1) Environment-API Graph Interactions to gather varied high-quality trajectories with targeted tool, 2) Advanced Tool-Query Synthesis to simplify hard query construction, and 3) Guided Iterative Chain for sophisticated CoT generation. Evaluations on Berkeley Function-Calling Leaderboard (BFCLv3) demonstrate the power of our framework: a 4B model built upon FunReason-MT generated data achieves state-of-the-art performance among comparable-sized models. Further performance improvements on BFCLv4 confirm that FunReason-MT provides a reliable and robust source for agentic learning.