# KAT-Coder-V2.5 Technical Report

arXiv: https://arxiv.org/abs/2607.05471 · HTML: https://mlsanity.com/paper/2607.05471/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 36 of its 54 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 36)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Graph Contrastive Learning with Adaptive Augmentation](https://mlsanity.com/paper/2010.14945/) (2020)
- [Graph-based Anomaly Detection and Description: A Survey](https://mlsanity.com/paper/1404.4679/) (2014)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [Structural Deep Clustering Network](https://mlsanity.com/paper/2002.01633/) (2020)
- [SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations](https://mlsanity.com/paper/2306.10759/) (2023)
- [Towards Unsupervised Deep Graph Structure Learning](https://mlsanity.com/paper/2201.06367/) (2022)
- [Large-Scale Learnable Graph Convolutional Networks](https://mlsanity.com/paper/1808.03965/) (2018)
- [Structural Entropy Guided Graph Hierarchical Pooling](https://mlsanity.com/paper/2206.13510/) (2022)
- [Cluster-guided Contrastive Graph Clustering Network](https://mlsanity.com/paper/2301.01098/) (2023)
- [Dink-Net: Neural Clustering on Large Graphs](https://mlsanity.com/paper/2305.18405/) (2023)
- [A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource](https://mlsanity.com/paper/2211.12875/) (2022)
- [DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering](https://mlsanity.com/paper/2212.05853/) (2022)
- [Neighbor Contrastive Learning on Learnable Graph Augmentation](https://mlsanity.com/paper/2301.01404/) (2023)
- [CONVERT:Contrastive Graph Clustering with Reliable Augmentation](https://mlsanity.com/paper/2308.08963/) (2023)
- [LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clustering](https://mlsanity.com/paper/2405.11801/) (2024)
- [Unsupervised Social Bot Detection via Structural Information Theory](https://mlsanity.com/paper/2404.13595/) (2024)
- [Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective](https://mlsanity.com/paper/2406.14288/) (2024)
- [Reinforcement Graph Clustering with Unknown Cluster Number](https://mlsanity.com/paper/2308.06827/) (2023)
- [Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection](https://mlsanity.com/paper/2312.11891/) (2023)
- [Hierarchical State Abstraction Based on Structural Information Principles](https://mlsanity.com/paper/2304.12000/) (2023)
- [SCGC : Self-Supervised Contrastive Graph Clustering](https://mlsanity.com/paper/2204.12656/) (2022)

## Built on by (most cited first, 4 of 4)

- [Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization](https://mlsanity.com/paper/2607.22334/) (2026)
- [Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models](https://mlsanity.com/paper/2608.16647/) (2026)
- [MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning](https://mlsanity.com/paper/2610.01352/) (2026)
- [Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk](https://mlsanity.com/paper/2610.14460/) (2026)

## Abstract (arXiv)

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 https://streamlake.com/product/kat-coder.