Ling & Ring 2.6 technical report is out, with two open-weight base models.
We co-design model + system across architecture, training, and agentic capability:
• 7:1 hybrid linear attention
• KPop for stable agentic RL: SWE-bench Verified 76.28%
• ~4× token efficiency
Architecture · Hybrid Linear Attention
GQA attention becomes costly and fragile at 256K context.
Ling 2.6 makes 256K practical through a hybrid design: 7 Lightning Attention layers + 1 MLA layer.
RL Training · From IcePop to KPop
IcePop (Ring-1T) used a uniform KL constraint for stable RL on MoE. But token-level mismatch is heterogeneous, which means rare tokens need wider tolerance.
KPop replaces the uniform bound with adaptive Binary KL.
As a result, our SWE-bench Verified improved from 70.8% → 76.28%, with pure RL.
Efficiency · Intelligence Density Over Token Count
Ling-2.6-1T reaches AAII 34 with ~16M output tokens — comparable to GPT-5.4 in non-reasoning mode, with ~4× higher token efficiency than Ling-2.0-1T.
Methods: Evo-CoT, LPO, Bidirectional RLHF, Shortest-correct Distillation.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
Why it matters
The report gives the architecture and RL recipe behind a 76.28% SWE-benchThe standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.Full definition → score, and the released base checkpoints let those training choices be tested rather than taken on trust.
Read the full thread on X ↗
