# LegalOne: A Family of Foundation Models for Reliable Legal Reasoning arXiv: https://arxiv.org/abs/2602.00642 ยท HTML: https://mlsanity.com/paper/2602.00642/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. - Builds on 31 of its 59 references that are in the map. - First posted on arXiv 31 Jan 2026. ## Placed in - LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/) ## Builds on (most cited first, 30 of 31) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021) - [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025) - [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023) - [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025) - [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025) - [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023) - [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025) - [MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies](https://mlsanity.com/paper/2404.06395/) (2024) - [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025) - [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025) - [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024) - [SaulLM-7B: A pioneering Large Language Model for Law](https://mlsanity.com/paper/2403.03883/) (2024) - [Continual Pre-Training of Large Language Models: How to (re)warm your model?](https://mlsanity.com/paper/2308.04014/) (2023) - [Simple and Scalable Strategies to Continually Pre-train Large Language Models](https://mlsanity.com/paper/2403.08763/) (2024) - [Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture](https://mlsanity.com/paper/2306.16092/) (2023) - [A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law](https://mlsanity.com/paper/2405.01769/) (2024) - [MathPile: A Billion-Token-Scale Pretraining Corpus for Math](https://mlsanity.com/paper/2312.17120/) (2023) - [WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models](https://mlsanity.com/paper/2308.10755/) (2023) - [LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model](https://mlsanity.com/paper/2406.04614/) (2024) - [OpenDataLab: Empowering General Artificial Intelligence with Open Datasets](https://mlsanity.com/paper/2407.13773/) (2024) - [Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data](https://mlsanity.com/paper/2510.03264/) (2025) - [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025) - [Mid-Training of Large Language Models: A Survey](https://mlsanity.com/paper/2510.06826/) (2025) - [LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain](https://mlsanity.com/paper/2508.12281/) (2025) - [Evaluation Ethics of LLMs in Legal Domain](https://mlsanity.com/paper/2403.11152/) (2024) - [CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation](https://mlsanity.com/paper/2502.17943/) (2025) - [Learning Dynamics in Continual Pre-Training for Large Language Models](https://mlsanity.com/paper/2505.07796/) (2025) ## Built on by (most cited first, 5 of 5) - [DataComp-VLM: Improved Open Datasets for Vision-Language Models](https://mlsanity.com/paper/2606.28551/) (2026) - [LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning](https://mlsanity.com/paper/2606.24901/) (2026) - [LexKairos: Benchmarking Legal Temporal Capabilities in LLMs](https://mlsanity.com/paper/2608.09106/) (2026) - [HuatuoGPT-3: RL-Only Domain Adaptation from Base Models](https://mlsanity.com/paper/2610.05966/) (2026) - [LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation](https://mlsanity.com/paper/2610.18299/) (2026) ## Abstract (arXiv) While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain knowledge and complexity of performing rigorous multi-step judicial reasoning. To address this gap, we present LegalOne, a family of foundational models specifically tailored for the Chinese legal domain. LegalOne is developed through a comprehensive three-phase pipeline designed to master legal reasoning. First, during mid-training phase, we propose Plasticity-Adjusted Sampling (PAS) to address the challenge of domain adaptation. This perplexity-based scheduler strikes a balance between the acquisition of new knowledge and the retention of original capabilities, effectively establishing a robust legal foundation. Second, during supervised fine-tuning, we employ Legal Agentic CoT Distillation (LEAD) to distill explicit reasoning from raw legal texts. Unlike naive distillation, LEAD utilizes an agentic workflow to convert complex judicial processes into structured reasoning trajectories, thereby enforcing factual grounding and logical rigor. Finally, we implement a Curriculum Reinforcement Learning (RL) strategy. Through a progressive reinforcement process spanning memorization, understanding, and reasoning, LegalOne evolves from simple pattern matching to autonomous and reliable legal reasoning. Experimental results demonstrate that LegalOne achieves state-of-the-art performance across a wide range of legal tasks, surpassing general-purpose LLMs with vastly larger parameter counts through enhanced knowledge density and efficiency. We publicly release the LegalOne weights and the LegalKit evaluation framework to advance the field of Legal AI, paving the way for deploying trustworthy and interpretable foundation models in high-stakes judicial applications.