We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.
Figures & tables
Figure 1: Results on 15 selected benchmarks. Among the six compared models, Sage S2.1 Flash ranks first on four of these benchmarks and second on seven. Scores are displayed to one decimal place.
Figure 2: Overview of Sage S2.1 Flash . We use a shared language backbone that integrates text, images, and scientific inputs to support general-purpose and scientific tasks.
Figure 3: Overview of Sage Sci-Perception. Scientific inputs are encoded into local states and projected into continuous embeddings for the Sage S2.1 Flash model.
Figure 4: Overview of ToolSpace. A tool-centric framework for cross-environment data synthesis that improves long-horizon agentic tool use.
Source or material
Count
Notes
Kaggle sources
4,936
Deduplicated index: 2,660 dataset sources and 2,276 competition sources.
Hugging Face data entries
129
Public dataset candidates.
GitHub data releases
144
Public dataset candidates, rather than counts of retrieved code repositories.
Official sites and other open stores
427
Public dataset candidates.
Research papers
2,960
Entries in the checked input list.
Hugging Face base models
11
Model cards: 10 released and 1 quarantined.
Table 1: Sources and materials for task synthesis. Candidate inventory sizes do not represent counts of final training tasks.
Figure 5: Overview of the CUA training data construction pipeline of Sage S2.1 Flash: Real-world tasks are collected and scaled through seed-based task synthesis, followed by agent rollouts in interactive environments to generate execution trajectories, which are subsequently filtered through outcome verification and rejection sampling to obtain high-quality training data.
Benchmark
Sage S2.1 Flash
GLM-5.3- Flash
DeepSeek-V4.1- Flash-1017
Qwen3.8- Max
GPT-5.6 Sol
Claude Opus 5
GPT-6 Astra
GPT-6.1 Sol
Claude Opus 5.5
Agentic Coding
Terminal-Bench 2.1
87.9
84.3
87.6
89.6
86.2
90.2
87.4
–
87.6
DeepSWE
67.9
63.7
73.9
67.0
70.6
72.6
74.1
75.2
74.2
NL2Repo-Bench
57.2
53.0
62.7
63.2
60.7
79.9
–
–
–
SWE-bench Pro
60.6
60.3
61.8
65.3
59.8
76.5
–
–
89.9
Productivity
Table 2: Results across 33 benchmarks. Bold scores mark the best result among Sage S2.1 Flash and the five primary baselines. The three columns on the right reproduce published leading-model results. Dashes indicate unavailable scores.
Figure 6: Human-guided iterative trajectory analysis. Left: the coordinator verifies and pairs trajectories, schedules analysis, and retrieves requested tool calls, code changes, execution feedback, and artifacts. Lower center: the analyzer inspects records, requests evidence, and develops an explanation, which a separate invocation counterreviews; bidirectional arrows represent on-demand retrieval. Upper center: cycle synthesis proposes the next round’s case focus, evidence requests, and review criteria. Dashed elements denote proposals for subsequent analysis. Right: case findings retain evidence and interpretive limits for human review. The cycle supports both broader coverage of cases and questions and closer inspection of the evidence behind each explanation.
Figure 7: CT reconstruction: orientation matching, sequence recovery, and skeletal visualization in 3D Slicer.
Figure 8: Reference-guided architectural and mechanical modeling in Blender and CAD.
Figure 9: Scientific software workflows with visual checks of segmentation, signal processing, and water-area change.
Figure 10: The Memory of Light: three interactive views connecting physical parameters, simulated responses, and source literature.
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not only to solve individual tasks, but also to organize work and revise its approach during execution. Sage-A1.5 highlights three improvements: agentic orchestration, verification, and open scientific discovery. First, agentic orchestration extends single-agent execution through task delegation and parallel collaboration among subagents with isolated contexts, enabling complex tasks to be decomposed and addressed concurrently and supporting efficient execution while reducing interference across concurrent subagents. Second, agentic verification strengthens long-horizon reliability through progress checking, evidence validation, and reflective strategy revision, allowing the agent to recognize unproductive search paths and pursue alternative approaches. Third, open scientific discovery extends agentic capabilities beyond answering predefined questions to conducting exploratory research, connecting scientific inquiry with interactive analysis and inspectable research artifacts. We showcase these capabilities through complicated agentic tasks and multidisciplinary scientific applications. Besides, we hope Sage-A1.5 provides the community with an accessible foundation for open scientific discovery, offering a practical path from long-horizon task execution to collaborative, verifiable, and inspectable scientific exploration.
We introduce Micius-Flash, a 27-billion-parameter model for engineering with native multimodal input, deep reasoning and a 256K-token context window. We design the Micius data pipeline as a knowledge-tree-driven data flywheel comprising three stages: knowledge tree construction and expansion, data synthesis, and quality validation with hard-example augmentation. From this data, we train expert models for semiconductor knowledge and reasoning, hardware coding, and semiconductor multimodal understanding, along with agentic experts. Subsequently, we employ Multi-Teacher On-Policy Distillation (MOPD) to supervise training on sequences generated by Micius itself, thereby integrating the capabilities of these expert models into a unified model. On more than 20 datasets with about 15K records, Micius-Flash averages 64.2% on hardware code benchmarks, 15.0 points above a same-size baseline. It scores 62.4% on a semiconductor-specific agent benchmark, exceeding the same-size baseline by 17.2 points. We further develop Micius Harness for industrial applications, connecting the model to specialized tools, including EDA tools and KiCad, as well as execution environments. Case studies in PCB design, chip design workflow automation, and software development demonstrate the model's ability to use tool execution feedback for multi-step planning, code debugging, and iterative verification. We release Micius as an open-source model to advance the development of agents for science and engineering.
Scientific papers require models to integrate evidence across text, equations, figures, tables, code, and datasets while preserving its provenance. Beyond answer correctness, scientific reading requires verifiable outputs from operations such as evidence localization, definition extraction, and consistency checking. We introduce SciDocBench, a workflow-centered benchmark targeting these operations through 124 expert-authored and difficulty-screened questions across seven research-assistant capability groups, 19 subtasks, and five scientific domains. Each question is instantiated in four matched settings formed by pairing its bilingual variants with the All Images First and Markdown Interleaved document representations, yielding 496 evaluation instances. The strongest evaluated model, Claude-Opus-5, scores 62.6 out of 100, with remaining gaps in evidence localization, structured information extraction, cross-document synthesis, and robustness to document representation. To convert these diagnostics into scalable training signals, we introduce SciDocIR, a structured representation of scientific document objects, layout and cross-reference relations, and provenance. Using SciDocIR, we construct SciDocDataset, which contains 4K supervised fine-tuning instances and 10K reinforcement-learning instances, built on 14 verifiable training subtasks. Post-training Qwen3.6-27B on task-aligned data improves its SciDocBench score from 40.03 to 45.33 with supervised fine-tuning and to 45.74 with subsequent reinforcement learning. Both adapted models preserve DocVQA and InfoVQA performance and improve ChartQA accuracy over the original model by 0.80 and 3.40 points, respectively. Together, SciDocBench, SciDocIR, and SciDocDataset connect capability diagnosis with verifiable training-data construction for scientific-document assistants.
Shenxi Wu, Yuhong Liu, Haosong Zhang +8
The Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory · New York University +5