{"slug": "kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training", "title": "Kat-Coder-v2.5 Technical Report (Qwen3.6-35B-A3B base for post-training)", "summary": "Researchers released KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real executable repositories, achieving the best agentic tool-use result on PinchBench and ranking second only to Opus 4.8 on repository-level software engineering benchmarks. The model's development addressed bottlenecks in reproducible environments, verifiable rewards, and high-value trajectories through an end-to-end agentic post-training framework including AutoBuilder and KwaiClawEnv, and scaled reinforcement learning with harness randomization and multi-teacher distillation.", "body_md": "# Computer Science > Software Engineering\n\n[Submitted on 6 Jul 2026]\n\n# Title:KAT-Coder-V2.5 Technical Report\n\n[View PDF](/pdf/2607.05471)\n\n[HTML (experimental)](https://arxiv.org/html/2607.05471v1)\n\nAbstract:We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capability is bottlenecked less by model scale than by the scarcity of reproducible environments, verifiable rewards, and high-value trajectories, which we address with an end-to-end agentic post-training framework. AutoBuilder reconstructs multilingual repositories into sandboxed environments with fail-to-pass and pass-to-pass verification at scale, from which we regenerate self-contained task specifications, recover near-miss trajectories, and distill supervision through process-aware filtering, while KwaiClawEnv synthesizes large-scale tool-use trajectories from executable services and real task seeds. 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, and unify SWE, Agent-Claw, and WebCoding experts via Multi-Teacher On-Policy Distillation. Across six software-engineering and agentic benchmarks, KAT-Coder-V2.5 delivers the best agentic tool-use result on PinchBench and ranks second only to the frontier Opus 4.8 on repository-level software engineering. Our service is available at[this https URL].\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training", "canonical_source": "https://arxiv.org/abs/2607.05471", "published_at": "2026-07-24 04:05:44+00:00", "updated_at": "2026-07-24 04:22:32.215107+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models", "developer-tools"], "entities": ["KAT-Coder-V2.5", "Opus 4.8", "PinchBench", "AutoBuilder", "KwaiClawEnv", "Qwen3.6-35B-A3B"], "alternates": {"html": "https://wpnews.pro/news/kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training", "markdown": "https://wpnews.pro/news/kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training.md", "text": "https://wpnews.pro/news/kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training.txt", "jsonld": "https://wpnews.pro/news/kat-coder-v2-5-technical-report-qwen3-6-35b-a3b-base-for-post-training.jsonld"}}