# A Survey on Post-training of Large Language Models

arXiv: https://arxiv.org/abs/2503.06072 · HTML: https://mlsanity.com/paper/2503.06072/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- First posted on arXiv 8 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Built on by (most cited first, 30 of 54)

- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy](https://mlsanity.com/paper/2507.01352/) (2025)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning](https://mlsanity.com/paper/2504.20024/) (2025)
- [Scaling Image and Video Generation via Test-Time Evolutionary Search](https://mlsanity.com/paper/2505.17618/) (2025)
- [Contextual Integrity in LLMs via Reasoning and Reinforcement Learning](https://mlsanity.com/paper/2506.04245/) (2025)
- [Agentic Robot: A Brain-Inspired Framework for Vision-Language-Action Models in Embodied Agents](https://mlsanity.com/paper/2505.23450/) (2025)
- [We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems](https://mlsanity.com/paper/2506.13666/) (2025)
- [Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities](https://mlsanity.com/paper/2503.17979/) (2025)
- [Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator](https://mlsanity.com/paper/2505.16690/) (2025)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [Reasoning Beyond Limits: Advances and Open Problems for LLMs](https://mlsanity.com/paper/2503.22732/) (2025)
- [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025)
- [CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning](https://mlsanity.com/paper/2505.13271/) (2025)
- [Co-Reinforcement Learning for Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2505.17534/) (2025)
- [Pre-Trained Policy Discriminators are General Reward Models](https://mlsanity.com/paper/2507.05197/) (2025)
- [Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning](https://mlsanity.com/paper/2506.01748/) (2025)
- [Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs](https://mlsanity.com/paper/2510.16062/) (2025)
- [Taming the Long-Tail: Efficient Reasoning RL Training with Adaptive Drafter](https://mlsanity.com/paper/2511.16665/) (2025)
- [Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs](https://mlsanity.com/paper/2508.16347/) (2025)
- [Exploring the Necessity of Reasoning in LLM-based Agent Scenarios](https://mlsanity.com/paper/2503.11074/) (2025)
- [Pelican-VL 1.0: A Foundation Brain Model for Embodied Intelligence](https://mlsanity.com/paper/2511.00108/) (2025)
- [Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning](https://mlsanity.com/paper/2506.04611/) (2025)
- [Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning](https://mlsanity.com/paper/2602.01745/) (2026)
- [Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition](https://mlsanity.com/paper/2503.12303/) (2025)
- [Evaluation of LLMs for mathematical problem solving](https://mlsanity.com/paper/2506.00309/) (2025)
- [UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data Selection](https://mlsanity.com/paper/2505.12457/) (2025)
- [Reinforcement Mid-Training](https://mlsanity.com/paper/2509.24375/) (2025)
- [Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning](https://mlsanity.com/paper/2604.07941/) (2026)
- [UniErase: Towards Balanced and Precise Unlearning in Language Models](https://mlsanity.com/paper/2505.15674/) (2025)

## Abstract (arXiv)

The emergence of Large Language Models (LLMs) has fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration. However, their pre-trained architectures often reveal limitations in specialized contexts, including restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance. These challenges necessitate advanced post-training language models (PoLMs) to address these shortcomings, such as OpenAI-o1/o3 and DeepSeek-R1 (collectively known as Large Reasoning Models, or LRMs). This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Efficiency, which optimizes resource utilization amidst increasing complexity; Integration and Adaptation, which extend capabilities across diverse modalities while addressing coherence issues. Charting progress from ChatGPT's alignment strategies to DeepSeek-R1's innovative reasoning advancements, we illustrate how PoLMs leverage datasets to mitigate biases, deepen reasoning capabilities, and enhance domain adaptability. Our contributions include a pioneering synthesis of PoLM evolution, a structured taxonomy categorizing techniques and datasets, and a strategic agenda emphasizing the role of LRMs in improving reasoning proficiency and domain flexibility. As the first survey of its scope, this work consolidates recent PoLM advancements and establishes a rigorous intellectual framework for future research, fostering the development of LLMs that excel in precision, ethical robustness, and versatility across scientific and societal applications.