Sage S2.1 Flash Technical Report

Published
Source
arXiv
Paper number
1483
Field
Machine Learning
arXiv ID
2611.21072

Key points

  • Sage Sci-Perception connects dedicated encoders for molecular graphs and biological sequences and numerical spectrum patches to the shared backbone.
  • The team built verifiable environments for tool use, search, and coding where task completion is checked against execution results.
  • ToolSpace built 77,760 tool-call pattern nodes from 2,042 distinct tools and organized them into 804 environments.
  • Among 33 benchmarks, the model ranked first on OfficeQA Pro (72.2), MLE-bench Lite (90.3), Harvey LAB, and SpreadsheetBench 2.
  • It ranked second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2).
  • Generated SFT trajectories averaged 18.86 tool calls, reaching up to 209.

Paper links

External research summaries. These are not HDATF publications or measured product results.

Read original (opens in a new tab)