KAT-Coder-V2 Technical Report

• URL: http://arxiv.org/abs/2603.27703v1
• Date: Sun, 29 Mar 2026 14:01:35 GMT
• Title: KAT-Coder-V2 Technical Report
• Abstract summary: We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou.<n>KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains.<n>We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances.
• Score: 45.53423367042574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou. KAT-Coder-V2 adopts a "Specialize-then-Unify" paradigm that decomposes agentic coding into five expert domains - SWE, WebCoding, Terminal, WebSearch, and General - each undergoing independent supervised fine-tuning and reinforcement learning, before being consolidated into a single model via on-policy distillation. We develop KwaiEnv, a modular infrastructure sustaining tens of thousands of concurrent sandbox instances, and scale RL training along task complexity, intent alignment, and scaffold generalization. We further propose MCLA for stabilizing MoE RL training and Tree Training for eliminating redundant computation over tree-structured trajectories with up to 6.2x speedup. KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs. Claude Opus 4.6 at 80.8%), 88.7 on PinchBench (surpassing GLM-5 and MiniMax M2.7), ranks first across all three frontend aesthetics scenarios, and maintains strong generalist scores on Terminal-Bench Hard (46.8) and tau^2-Bench (93.9). Our model is publicly available at https://streamlake.com/product/kat-coder.

Related papers

• ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search [54.43696074323815]
  ZGCM-1 is a fully open 7B foundation model trained from scratch with extreme data, system, and algorithmic efficiency.<n>We establish an AI-native R&D workflow where agent swarms autonomously manage cluster operations.<n>ZGCM-1-7B is competitive across 7B model family on general benchmarks.
  arXiv  Detail & Related papers  (2026-09-11T17:18:04Z)
• KAT-Coder-V2.5 Technical Report [61.907486544595336]
  KAT-Coder-V2.5 is a coding-focused agentic model trained to act autonomously inside real, executable repositories.<n>It reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale.<n>We further scale reinforcement learning with harness randomization, a reliability-hardened sandbox, an asymmetric actor--critic PPO with hindsight-augmented value estimation, and a harness-oriented reward framework.
  arXiv  Detail & Related papers  (2026-07-06T08:14:02Z)
• HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools [2.0320563270126493]
  We present HyDRA, a framework that predicts fine-grained, multi-dimensional capability requirements per query.<n>A shortfall-matching algorithm then selects the cheapest model whose capabilities meet the predicted requirements.<n>The framework is deployed to all users in GitHub Copilot's VS Code Chat auto-mode.
  arXiv  Detail & Related papers  (2026-05-16T18:19:30Z)
• Orchard: An Open-Source Agentic Modeling Framework [124.68499958175111]
  We present Orchard, an open-source framework for scalable agentic modeling.<n>At its core is Orchard Env, a lightweight environment service providing reusable primitives for sandbox lifecycle management.<n>On top of Orchard Env, we build three agentic modeling recipes.
  arXiv  Detail & Related papers  (2026-05-14T16:35:12Z)
• Composer 2 Technical Report [93.84516486051359]
  Composer 2 is a specialized model designed for agentic software engineering.<n>The model is trained in two phases: first, continued pretraining to improve the model's knowledge and latent coding ability.<n>We develop infrastructure to support training in the same Cursor harness that is used by the deployed model.
  arXiv  Detail & Related papers  (2026-03-25T16:18:37Z)
• Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models [49.911784762244814]
  TraceRL is a trajectory-aware reinforcement learning framework for diffusion language models (DLMs)<n>We derive a series of state-of-the-art diffusion language models, namely TraDo.<n>TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• Kimi K2: Open Agentic Intelligence [118.78600121345099]
  Kimi K2 is a large language model with 32 billion activated parameters and 1 trillion total parameters.<n>Based on MuonClip, K2 was pre-trained on 15.5 trillion tokens with zero loss spike.<n>Kimi K2 achieves state-of-the-art performance among open-source non-thinking models.
  arXiv  Detail & Related papers  (2025-07-28T05:35:43Z)
• Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning [48.66688117533318]
  We propose CURE, a novel reinforcement learning framework with a dedicated reward design.<n>CURE co-evolves coding and unit test generation capabilities based on their interaction outcomes.<n>We find that our model can serve as an effective reward model for reinforcement learning on base models.
  arXiv  Detail & Related papers  (2025-06-03T17:58:42Z)
• ACECODER: Acing Coder RL via Automated Test-Case Synthesis [36.740393665032954]
  We design a pipeline that generates extensive (question, test-cases) pairs from existing code data.<n>We construct preference pairs based on pass rates over sampled programs to train reward models with Bradley-Terry loss.<n>We show that our RL training can improve model on HumanEval-plus by over 25% and MBPP-plus by 6% for merely 80 optimization steps.
  arXiv  Detail & Related papers  (2025-02-03T18:46:04Z)

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.