KAT-Coder Technical Report

• URL: http://arxiv.org/abs/2510.18779v3
• Date: Fri, 31 Oct 2025 04:09:36 GMT
• Title: KAT-Coder Technical Report
• Authors: Zizheng Zhan, Ken Deng, Jinghui Wang, Xiaojiang Zhang, Huaixi Tang, Minglei Zhang, Zhiyi Lai, Haoyang Huang, Wen Xiang, Kun Wu, Wenhao Zhuang, Shaojie Wang, Shangpeng Yan, Kepeng Lei, Zongxian Feng, Huiming Wang, Zheng Lin, Mengtong Li, Mengfei Xie, Yinghan Cui, Xuxing Chen, Chao Wang, Weihao Li, Wenqiang Zhu, Jiarong Zhang, Jingxuan Xu, Songwei Yu, Yifan Yao, Xinping Lei, C. Zhang, Han Li, Junqi Xiong, Zuchen Gao, Dailin Li, Haimo Li, Jiaheng Liu, Yuqun Zhang, Junyi Peng, Haotian Zhang, Bin Chen,
• Abstract summary: KAT-Coder is a large-scale agentic code model trained through a multi-stage curriculum encompassing Mid-Term Training, Supervised Fine-Tuning (SFT), Reinforcement Fine-Tuning (RFT), and Reinforcement-to-Deployment Adaptation.<n>These stages enable KAT-Coder to achieve robust tool-use reliability, instruction alignment, and long-context reasoning.
• Score: 48.00975798131211
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development workflows. However, bridging the gap between static text-based training and dynamic real-world agentic execution remains a core challenge. In this technical report, we present KAT-Coder, a large-scale agentic code model trained through a multi-stage curriculum encompassing Mid-Term Training, Supervised Fine-Tuning (SFT), Reinforcement Fine-Tuning (RFT), and Reinforcement-to-Deployment Adaptation. The Mid-Term stage enhances reasoning, planning, and reflection capabilities through a corpus of real software engineering data and synthetic agentic interactions. The SFT stage constructs a million-sample dataset balancing twenty programming languages, ten development contexts, and ten task archetypes. The RFT stage introduces a novel multi-ground-truth reward formulation for stable and sample-efficient policy optimization. Finally, the Reinforcement-to-Deployment phase adapts the model to production-grade IDE environments using Error-Masked SFT and Tree-Structured Trajectory Training. In summary, these stages enable KAT-Coder to achieve robust tool-use reliability, instruction alignment, and long-context reasoning, forming a deployable foundation for real-world intelligent coding agents. Our KAT series 32B model, KAT-Dev, has been open-sourced on https://huggingface.co/Kwaipilot/KAT-Dev.

Related papers

• ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas [13.919124676472022]
  ASTRA is an end-to-end framework for training tool-augmented language model agents.<n>ASTRA integrates scalable data synthesis and verifiable reinforcement learning.<n> Experiments on multiple agentic tool-use benchmarks demonstrate that ASTRA-trained models achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-01-29T11:22:23Z)
• daVinci-Dev: Agent-native Mid-training for Software Engineering [22.845876048950483]
  We present a systematic study of agentic mid-training, establishing the data synthesis principles and training methodology for effective agent development at scale.<n>We demonstrate our superiority over the previous open software engineering mid-training recipe Kimi-Dev under two post-training settings with an aligned base model and agentic scaffold.
  arXiv  Detail & Related papers  (2026-01-26T12:20:18Z)
• Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models [78.73992315826035]
  We introduce Youtu-LLM, a lightweight language model that harmonizes high computational efficiency with native agentic intelligence.<n>Youtu-LLM is pre-trained from scratch to systematically cultivate reasoning and planning capabilities.
  arXiv  Detail & Related papers  (2025-12-31T04:25:11Z)
• DiRL: An Efficient Post-Training Framework for Diffusion Language Models [54.405206032785706]
  Diffusion Language Models (dLLMs) have emerged as promising alternatives to Auto-Regressive (AR) models.<n>Existing methods suffer from computational inefficiency and objective mismatches between training and inference.<n>We introduce DiRL, an efficient post-training framework that tightly integrates FlexAttention-accelerated blockwise training with LMDeploy-optimized inference.
  arXiv  Detail & Related papers  (2025-12-23T08:33:19Z)
• From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence [150.3696990310269]
  Large language models (LLMs) have transformed automated software development by enabling direct translation of natural language descriptions into functional code.<n>We provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs.<n>We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder)
  arXiv  Detail & Related papers  (2025-11-23T17:09:34Z)
• ACT: Bridging the Gap in Code Translation through Synthetic Data Generation & Adaptive Training [1.4709455282157278]
  Auto-Train for Code Translation (ACT) aims to improve code translation capabilities by enabling in-house finetuning of open-source Large Language Models (LLMs)<n>ACT's automated pipeline significantly boosts the performance of these models, narrowing the gap between open-source accessibility and the high performance of closed-source solutions.<n>Our results demonstrate that ACT consistently enhances the effectiveness of open-source models, offering businesses and developers a secure and reliable alternative.
  arXiv  Detail & Related papers  (2025-07-22T11:35:35Z)
• SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development [40.48114055515786]
  SWE-Dev is the first large-scale dataset designed to evaluate and train autonomous coding systems on real-world feature development tasks.<n>This collection provides high-quality data forSupervised Fine-Tuning (SFT), but also enables Reinforcement Learning (RL) by delivering accurate reward signals from executable unit tests.
  arXiv  Detail & Related papers  (2025-05-22T17:51:49Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents [50.82665351100067]
  FlowGen is a code generation framework that emulates software process models based on multiple Large Language Model (LLM) agents. We evaluate FlowGenScrum on four benchmarks: HumanEval, HumanEval-ET, MBPP, and MBPP-ET.
  arXiv  Detail & Related papers  (2024-03-23T14:04:48Z)
• ChatDev: Communicative Agents for Software Development [84.90400377131962]
  ChatDev is a chat-powered software development framework in which specialized agents are guided in what to communicate. These agents actively contribute to the design, coding, and testing phases through unified language-based communication.
  arXiv  Detail & Related papers  (2023-07-16T02:11:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.