Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
- Published
- Source
- arXiv
- Paper number
- 428
- Field
- LLMs / NLP
- arXiv ID
- 2606.15079
Key points
- It mixes Lightning Attention and MLA in a 7:1 ratio, which substantially reduces long-context FLOPs and KV-cache burden.
- Evo-CoT, LPO, and shortest-answer distillation improve token efficiency by about 4x compared with the 2.0 generation.
- KPop asynchronous agentic RL enables stable environment-based learning even at the 1T scale.
- Ring-2.6-1T records strong results on PinchBench at 87.60, ClawEval at 63.82, GAIA-2 Search, and tau2-Bench Telecom.
Paper links
External research summaries. These are not HDATF publications or measured product results.