LLM Post-Training

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

29 papers in the last four weeks, up 81% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 175

All topics

SDO: Structure-Aware Data Organization for Efficient LLM Post-Training
Jul 29, 2026Jinliang Gao, Ning Yang, Hai Wang +2Training Data Curation Efficient Language Model Training
Institute of Automation, Chinese Academy of Sciences · National University of Defense Technology
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
Jul 28, 2026Fanqing Meng, Lingxiao Du, Qiguang Chen +4LLM Agent Evaluation LLM Agent Self-Improvement
1Evolvent AI · 2National University of Singapore
Training Language Models to Cooperate with Inference-Time Controllers
Jul 26, 2026Moumita Choudhury, Vanshaj Khattar, Jing Liu +4RL for Language Model Reasoning LLM Post-Training
College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts, USA · Mitsubishi Electric Research Laboratories, Cambridge, Massachusetts, USA
Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids
Jul 22, 2026Roger Sala Sisó, Tiago Silvério, Jakob Sand +1Robotic Manipulation Vision-Language-Action Models
HIVE Robots, Denmark · Department of Engineering Technology, Technical University of Denmark, Denmark
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Jul 22, 2026Dongfang Li, Xiaodong Luo, Ruoyu Sun +62Communication-Efficient Distributed Training LLM Post-Training
Co-Harness: Co-Evolving Harnesses and Model Weights for LLM Agents
Jul 17, 2026Zhengyu Chen, Teng Xiao, Huaisheng Zhu +3Agent Harness Optimization LLM Agent Workflow Optimization
Meituan · Allen Institute for AI · Independent
Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration
Jul 15, 2026Shuhao Li, Guodong Du, Anhao Zhao +3Confidence Estimation in Language Models Language Model Calibration
Eastern Institute of Technology, Ningbo · The Hong Kong Polytechnic University
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Jul 13, 2026Daocheng Fu, Rong Wu, Yu Yang +7Large Language Model-Guided Optimization RL Post-Training
Shanghai AI Laboratory · Fudan University · Zhejiang University +2
How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift
Jul 10, 2026James Elcock, William F. Shen, Xinchi Qiu +1LLM Alignment LLM Post-Training
University of Cambridge
CurateEvo: Data-Curation Evolving for Agentic Post-Training
Jul 7, 2026Dingzirui Wang, Xuanliang Zhang, Keyan Xu +2Training Data Curation LLM Agent Training
Harbin Institue of Technology
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training
Jul 6, 2026Junze Ye, Jiayi Cheng, Miao Lu +3Supervised Fine-Tuning Data Augmentation
Stanford University · New York University
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Jul 2, 2026Zhuowei Chen, Xiang Lorraine LiOn-Policy Self-Distillation Training Data Selection
University of Pittsburgh, United States
Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training
Jul 2, 2026Xingtao Zhao, Tian Yang, Han JiangDomain Adaptation LLM Fine-Tuning
School of Cyber Science and Technology Beihang University Beijing, China · School of Information Renmin University of China Beijing, China
CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training
Jul 2, 2026Fangfei Li, Chenyang Zhao, Long Wang +3LLM Agent Evaluation LLM Post-Training
MatrixOrigin China · MatrixOrigin USA
Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Jul 2, 2026Meng Wang, Haohan Zhao, Wenzhuo Liu +7Continual Learning for LLMs On-Policy Self-Distillation
Centre for Artificial Intelligence and Robotics, HKISI, CAS · Institute of Automation, CAS · University of Chinese Academy of Sciences +1
Beyond Perplexity: A Behavioral Evaluation Framework for Deployment-Memory Claims in LLM Test-Time Training
Jul 1, 2026Xiangchen Song, Zhenhao Chen, Lingjing Kong +4LLM Evaluation LLM Memory
Carnegie Mellon University · MBZUAI
Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision
Jun 30, 2026Zifan Carl Guo, Laura Ruis, Jacob Andreas +1Counterfactual Explanations Faithfulness of Language Model Explanations
MIT EECS
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Jun 30, 2026Zhaojian Yu, Penghao Yin, Shuzheng Gao +3Tool-Augmented Language Model Agents LLM Tool Use
1Tsinghua University · 2The Chinese University of Hong Kong · 3Simple Agent Lab
When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon
Jun 29, 2026Huaqing Zhang, Jingchu Gai, Juno Kim +2Imitation Learning Interactive Imitation Learning
Tsinghua University · Carnegie Mellon University · UC Berkeley +1
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Jun 29, 2026Wenhan Ma, Jianyu Wei, Liang Zhao +10Multi-Teacher Knowledge Distillation On-Policy Distillation
Peking University · Xiaomi · LLM Core, Xiaomi +2
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
Jun 29, 2026Gan Luo, Zihan Qin, Bin Dong +1Zero-Shot Learning Meta-Learning
School of Mathematics Science, Peking University
Data and Evaluation Closed-Loop for Model Capability Enhancement
Jun 26, 2026Zhixuan Li, Jiangan Yuan, Han XuLLM Evaluation LLM Post-Training
Baidu Inc.
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Jun 26, 2026Changyue Li, Jiaming He, Youliang Yuan +4Supervised Fine-Tuning LLM Safety Alignment
The Chinese University of Hong Kong, Shenzhen · Ant Group · Lero the Research Ireland Centre for Software, University of Limerick
Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes
Jun 25, 2026Jeremias Ferrao, Niclas Müller-Hof, Iustin Sîrbu +2LLM Safety Evaluation LLM Post-Training
University of Groningen · University Politehnica of Bucharest · NVIDIA
NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research
Jun 25, 2026Qiaobo Hao, Yangqian Wu, Shunyi Wang +5Supervised Fine-Tuning RL for Language Models
ZTE NebulaL0 Post-Training Team
The Interplay of Harness Design and Post-Training in LLM Agents
Jun 24, 2026Kyungmin Kim, Youngbin Choi, Seoyeon Lee +3Agent Harness Optimization LLM Agents
Graduate School of Artificial Intelligence, POSTECH · Department of Computer Science and Engineering, POSTECH
AsyncOPD: How Stale Can On-Policy Distillation Be?
Jun 23, 2026Wonjun Kang, Kevin Galim, Seunghyuk Oh +9Language Model Distillation On-Policy Distillation
FuriosaAI · Ajou University · UC Berkeley +3
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Jun 22, 2026Xin Liu, Simin Ma, Shujian Liu +5Data-Free Knowledge Distillation Language Model Distillation
University of Michigan · 2Zoom Video Communications
CuratorKIT : Data Curation and Synthetic Data Generation for LLM Post-Training
Jun 19, 2026Soham Bhattacharjee, Karun Sharma, Vinay Kumar Sankarapu +1Training Data Curation Synthetic Data Generation for Language Models
Lexsi Labs
Which Pairs to Compare for LLM Post-Training?
Jun 17, 2026Jiangze Han, Vineet Goyal, Will MaPairwise Preference Learning Pairwise Comparison
Columbia University

Jul 29, 2026, cs.LGJ/K move · Enter open · S save

SDO: Structure-Aware Data Organization for Efficient LLM Post-Training

Jinliang Gao, Ning Yang, Hai Wang, Baili Xiao+1

Institute of Automation, Chinese Academy of Sciences · National University of Defense Technology

Training Data Curation Efficient Language Model Training LLM Post-Training Data-Efficient Learning

Open paper AskPDF arXiv

Post-training of large language models is expensive, and existing efficiency improvements mainly focus on selecting informative samples or designing training schedules. However, data organization itself is usually treated as a static preprocessing step: embedding-based grouping methods construct fixed partitions before training and cannot adapt to the evolving sample exposure during optimization. As a result, all samples receive similar exposure despite their different optimization needs, leading to redundant updates for some samples while leaving others under-optimized. To address this problem, we propose SDO (Structure-Aware Data Organization), a plug-and-play data organization framework with an exposure-driven feedback mechanism that organizes mini-batch composition and sample exposure according to representation-space structure. SDO operates epoch by epoch on frozen external embeddings, avoiding model warm-up training overhead: within each epoch, locality-aware batching forms coherent mini-batches via KNN neighborhood traversal; across epochs, exposure-balanced scheduling records per-sample participation and reduces the sampling probability of over-exposed samples to preserve long-term coverage. Across SFT, DPO, and GRPO, SDO accelerates convergence, with the largest gains observed in the early-to-mid phase, producing more coherent gradients and more balanced accuracy across question types without permanently excluding training samples.

Momentum

Related topics

Latest papers 175