Skip to content
Log in
Sponsored Have an interesting project or opportunity? → Hire me ↗
Sponsored Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt Design Multi-Agent AI Systems Using MCP and A2A: Engineer your own Pyt

NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research

Qiaobo Hao Yangqian Wu Shunyi Wang Zhongjian Zhang Ziqun Li Yayin He Muqing Li Chengli Zhong
Jun 2026 · arXiv.org · Vol abs/2606.26671 · 0 citations · 38 references
Computer Science

TL;DR

This report provides a fully reproducible empirical post-training recipe for 8B-scale LLMs, and comprehensively dissects the capability trade-offs among instruction adherence, mathematical reasoning, code generation and general knowledge.

Abstract

Post-training alignment determines the reasoning and human preference following capabilities of large language models, yet most existing works withhold detailed data construction, filtering rules and training recipes, which hinders community reproducibility and lightweight model optimization. This work presents NebulaExp, a fully transparent, ablation-driven post-training pipeline built on Qwen3-8B-base, covering two orthogonal model branches: general instruct model and complex reasoning-specialized model. We curate a raw corpus of 3.84M multi-source SFT samples and a 200K verifiable RL candidate pool, and design an end-to-end data processing stack including response distillation, multi-dimensional cross-verification filtering, fine-grained difficulty grading, task classification and diversity-aware sampling. For the Instruct branch, our three-stage optimized supervised fine-tuning approach NebulaExp-Ins-SFT improves the average benchmark score from the 55.01 baseline of Qwen3-8B-nothink to 60.99. GRPO reinforcement learning then further elevates the average score to 61.85. For the Reasoning branch, medium-difficulty GRPO RL improves average reasoning score from 73.88 to 75.17. To address RL's dependency on task verifiers, we systematically investigate single-teacher and multi-teacher OPD (MOPD): utilizing merely 4K instruction-following samples and outperforms RL baseline by 3.26 points on IFEval with +4.43 average overall gain; MOPD fuses four domain-specialist teachers with merely 10K samples, lifting average performance by 4.18 over the base model. This report provides a fully reproducible empirical post-training recipe for 8B-scale LLMs, and comprehensively dissects the capability trade-offs among instruction adherence, mathematical reasoning, code generation and general knowledge.

DOI arXiv Semantic Scholar
View source

Similar papers

Preprint Jul 2026

UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing

UltraX is proposed, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing.

Xinlong Zhao, Dongsheng Liu, Hengyu Zhao et al. · 0 citations
Preprint Jul 2026

USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning

Test-time adaptation (TTA) has emerged as a popular paradigm for improving the performance of vision-language models (e.g., CLIP) on downstream tasks. Among existing CLIP-based TTA methods, Test-Time Prompt Tuning (TPT) is a pioneering work that optimizes textual prompts using multiple test-time augmentations and remains a strong baseline to date. In this work, we revisit TPT and reveal that its optimization can be interpreted as implicitly learning from self-generated pseudo labels. Building on this perspective, we propose a unified self-ensembling framework (USE) that ensures consistency between the optimization and inference stages. During optimization, we introduce a simple yet effective self-ensembling (SE) strategy that emphasizes the test image itself over its augmented views adaptively to obtain more reliable pseudo labels. To fully exploit the potential of augmentations, we further apply the same strategy at inference time, unifying the objectives of both stages. Notably, SE can also act as a lightweight optimization-free TTA method. Extensive experiments across multiple datasets demonstrate that SE and USE outperform their counterparts, respectively. Furthermore, SE yields consistent performance gains when integrated with existing TTA methods. The code is available at https://github.com/sirujiang/USE.

Siru Jiang, Jian Liang, Ran He et al. · 0 citations
Preprint Aug 2026

Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge

Wnuan, a three-stage pipeline that constructs task-oriented supervision from documents, performs supervised fine-tuning with general-data replay, and applies reinforcement learning to residual errors is presented, describing both the gains and the general-capability cost of staged enterprise adaptation.

Xiaofeng Shi, Xiaosong Qiu, Wenxin Ma et al. · 0 citations
Preprint Jul 2026

PPL-Factory: Task-Aware and Budget-Aware Data Selection from Language Modeling to Reasoning

PPL-Factory is proposed, a simple and interpretable data selection framework that combines task-aware perplexity-based scores and data budget-aware selection criteria that outperforms other state-of-the-art data selection methods using only $1\%$ of the training set.

Hang Zhang, Warren J. Gross · 0 citations
Open access Aug 2026

Optimizing sample selection for large language model-based entity matching using AssistEM

AssistEM, a framework for efficient LLM adaptation to EM via principled data selection, demonstrates that selective fine-tuning not only accelerates adaptation but also improves training efficiency (requiring fewer GPU hours), enabling open-source LLMs to rival–and in some cases outperform–closed-source models.

John Bosco Mugeni, S. Lynden, Toshiyuki Amagasa et al. · 0 citations