Rohan Paul 谈 Qwen3.8-27B RL post-train 的智能体表现：幻觉率从 30.4% 降至 15.1%

Rohan Paul· @rohanpaul_ai · X·2026-10-20 22:08· 29 分钟前AI 评分56

AI 导读

Rohan Paul 观察到今年不少亮眼 Agent 结果来自小开源模型的 post-train。

正文 · 原文

Some of the most interesting agent results this year are coming out of post-trains of small open models.

A new RL post-train Qwen3.8-27B model trained with an open-source environments cuts the hallucination rate on AA-Omniscience from 30.4% to 15.1%.

the compressed copy of the mla version fits on my single 24 GB RTX 4090 and holds about 3.5x more context than base Qwen.

It beats GPT 6 Luna-medium on DeepSWE, placing in between Luna 6 medium and high.
scores higher on Terminal-Bench 2.1 while writing a median 23.8K output tokens per solved task, where base Qwen writes 54.9K.

Tried an unreleased version of this model, and really felt the comparative intelligent density, that it writes a lot less.

tops Muse Glimmer 30B and OpenAI’s GPT-6 Luna (high) on Terminal-Bench, τ³-bench, ClawEval and BFCL v4 (Berkeley Function Calling Leaderboard), though Luna still wins DeepSWE at 53.1%.

They also released an MLA version, which is the same model with its 16 full-attention layers converted to multi-head latent attention, which shrinks the memory each token takes from 64 KiB to 18 KiB so far more or longer sessions fit on one GPU.

来源：Rohan Paul · x.com