Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Mode
We present Nanbeige4.2-3B, a compact general agentic model with 3B non-embedding parameters. It delivers strong performance across code-agent, office-agent, and complex tool-use tasks while maintaining highly competitive reasoning capabilities in mathematics, coding, and science. Nanbeige4.2-3B is pretrained from scratch on 28T tokens with a Looped Transformer that reuses the layer stack to increase capacity without adding parameters. For SFT data and trajectory construction, we expand the diver
Record details
Published: 24 July 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy
Retrieved: 27 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The machine can say it but cannot hear it. Designed affective patterns and the expressive-sensing asymmetry in human-machine communication
arXiv cs.HC · 24 July 2026
One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments
arXiv cs.AI · 24 July 2026
Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents
arXiv cs.AI · 24 July 2026
DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents
arXiv cs.AI · 24 July 2026
Learning Spatiotemporal Decision Priors for Efficient Path Planning under Partial Observability
arXiv cs.AI · 24 July 2026
Agent Security Needs Redefinition through a Holistic Framework
arXiv · 24 July 2026
How to cite this record
ethics.ai (24 July 2026), “Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Mode,” evidence record 13622, https://ethics.ai/record/13622 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.