Curing LLM overthinking in 3 weeks: 27B reasoning median cut from 32K to 4K without losing accuracy

青稞AI · wechat · 2026-09-06

A detailed engineering writeup from the Qingke community on a three-week post-training campaign against overthinking in Qwen3.8-27B. The model wasn't unable to solve problems—it just thought endlessly on them: in GPQA, correct answers had a median reasoning of 3,627 tokens while wrong ones hit the 32,768 cap, with 26 truncations of which 22 were ultimately wrong.

The three-week arc:

Results: Week-3 SFT hit 168/198 (84.85%) with zero timeouts. All three RLVR checkpoints failed capability checks but yielded a data asset; a final 5-step SimPO run on 110 curated preference pairs (57 pathology-repair + 53 capability-protection, with 36 rejected traces kept over 32K) punished only "not finishing the task," never length itself.

Key lesson: effective behavior training needs all three data types—native correct traces, same-problem failures, and teacher solutions. A heavily post-trained model needs targeted treatment, not bulk data.

Original post →

More from Models

Models channel →