GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Minbyul
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Minbyul
Model Tree
Qwen/Qwen3.5-35B-A3B
Input Modalities
Output Modalities
Supported Functionality
Full-parameter supervised fine-tuning on a Megatron-based distributed training stack. Identical recipe to the sibling arms; only the data intervention differs.
| Hyperparameter | Value |
|---|---|
| Epochs | 2 |
| Global batch size | 128 |
| Learning rate | 5e-6, cosine decay to 5e-7 |
| Sequence length | 131,072 |
| Objective | token-level cross-entropy on assistant turns (trajectory imitation) |
The study's A–G taxonomy of over-reflection behaviors categorizes pathological patterns in browsing-agent trajectories — e.g., post-answer verification loops (the agent keeps searching after it has already stated the answer), redundant re-search after sufficient evidence has been gathered, and ungrounded reasoning not supported by retrieved content. In this arm, any trajectory carrying a pathological type is removed entirely. This is the coarsest intervention class in the study: it trades corpus size for corpus cleanliness, in contrast to the surgical editing of the Repair arm and the outcome-based filtering of the Correct arm.
| Arm | Intervention class |
|---|---|
| Asis | none — unmodified trajectory imitation baseline |
| Drop (this model) | typed whole-trajectory deletion of pathological over-reflection types |
| Repair | taxonomy-guided surgical repair (truncate post-evidence over-search tails; remove ungrounded trajectories) |
| Correct | correctness-filtered subset (deterministic answer matching) |
Research artifact. Intended for studying how removing pathological demonstrations (as opposed to editing them, or filtering by outcome) affects over-reflection, stopping behavior, and search efficiency in tool-using web agents. It expects a browsing-agent tool surface compatible with its training format (function-calling tools for web search, page opening, and in-page lookup).