KAT-Coder-V2 Technical Report

Fengxiang Li, Han Zhang, Haoyang Huang, Jinghui Wang, Jinhua Hao, Kun Yuan, Mengtong Li, Minglei Zhang, Pengcheng Xu, Wenhao Zhuang, Yizhen Shao, Zongxian Feng, Can Tang, Chao Wang, Chengxiao Tong, Fan Yang, Gang Xiong, Haixuan Gao, Han Gao, Hao Wang, Haochen Liu, Hongliang Sun, Jiabao Li, Jingwen Chang, Jun Du, Junyi Peng, Leizhen Cui, Meimei Jing, Mingqi Wu, Shangpeng Yan, Shaotong Qi, Suzhe Xu, Wenxuan Zhao, Xianda Sun, Xuan Xie, Yanbo Wang, Yao Xia, Yinghan Cui, Yingpeng Chen, Yong Wang, Yuze Shi, Zhiwei Shen, Ziyu Wang, Ming Sun, Lin Ye, Bin Chen · Mar 29, 2026 · Citations: 0

Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Low trust

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Low

Derived from extracted protocol signals and abstract evidence.

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.

Abstract-only analysis — low confidence

All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.

This paper looks adjacent to evaluation work, but not like a strong protocol reference.
The available metadata is too thin to trust this as a primary source.
The abstract does not clearly describe the evaluation setup.

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

Should You Rely On This Paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

Background context only.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Trust level

Low

Usefulness score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Weak / implicit signal

Usefulness for eval research

Adjacent candidate

Extraction confidence 25%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou."

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou."

Quality Controls

missing

Not reported

No explicit QC controls found.

"We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou."

Benchmarks / Datasets

partial

SWE Bench, SWE Bench Verified, Pinchbench, Terminal Bench

Useful for quick benchmark comparison.

"KAT-Coder-V2 achieves 79.6% on SWE-bench Verified (vs."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou."

Rater Population

partial

Domain Experts

Helpful for staffing comparability.

"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."

Human Feedback Details

Uses human feedback: No
Feedback types: None
Rater population: Domain Experts
Expertise required: Coding

Evaluation Details

Evaluation modes:
Agentic eval: None
Quality controls: Not reported
Evidence quality: Low
Use this page as: Background context only

Protocol And Measurement Signals

Benchmarks / Datasets

SWE-benchSWE-bench VerifiedPinchbenchTerminal-Bench

Reported Metrics

No metric terms were extracted from the available abstract.

Research Brief

Metadata summary

We present KAT-Coder-V2, an agentic coding model developed by the KwaiKAT team at Kuaishou.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

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.

Researcher Actions

Compare this paper against others mentioning SWE-bench.
Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
Use related-paper links to find stronger protocol-specific references.

Caveats

Generated from abstract + metadata only; no PDF parsing.
Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Expert verification evaluation SWE-bench

Research Summary

Contribution Summary

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…
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.

Why It Matters For Eval

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…

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Gap: Evaluation mode is explicit

No clear evaluation mode extracted.
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Pass: Benchmark or dataset anchors are present

Detected: SWE-bench, SWE-bench Verified, Pinchbench, Terminal-Bench
Gap: Metric reporting is present

No metric terms extracted.

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

No related papers found for this item yet.

Get Started

The #1 talent network for AI training.

Self-Service

Post a job, get a curated shortlist

Manage your team directly on-platform

Post a Job

Managed Service