16 papers
WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents
Weihao Li, Zihang Xu, Zhongqiu Wang +8
Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordina…
OPRD: On-Policy Reminder Distillation for Long-Horizon Coding Agents
Yuechen Luo, Zhiyi Lai, Miao Ziqi +9
Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across long interactions. However,…
SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution
Songwei Yu, Ziqi Miao, Jingxuan Xu +10
Historical code changes provide convenient task boundaries, but do not identify which production functions selected tests exercise or support composing validated behaviors beyond a…
TailSieve: Partial-Rollout-Guided Tail Routing for LLM Rollouts
Tianqi Xu, Lu Lv, Haoyang Huang +15
Large-scale rollouts have become a core component of modern LLM systems, spanning reinforcement learning (RL) post-training, on-policy distillation, and sampling-heavy evaluation.…
KAT-Coder-V2.5 Technical Report
Bo Huang, Fengxiang Li, Hao Xu +50
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 capabili…
DualEval: Joint Model-Item Calibration for Unified LLM Evaluation
Aaron J. Li, Hao Huang, Youngmin Park +6
Current LLM evaluation relies on two complementary but often disconnected signals: static benchmarks with objective correctness labels and arena-style preference data that better r…
DiT-Reward: Generative Representations for Text-to-Image Reward Modeling
Yuanming Yang, Guoqing Ma, Bo Wang +5
Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstream task of generative repres…
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
Xinping Lei, Xinyu Che, Junqi Xiong +16
Large language models are rapidly evolving into interactive coding agents capable of end-to-end web coding, yet existing benchmarks evaluate only narrow slices of this capability,…
CodeTracer: Towards Traceable Agent States
Han Li, Yifan Yao, Letian Zhu +13
Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks…
Sanity Checks for Agentic Data Science
Zachary T. Rewolinski, Austin V. Zane, Hao Huang +4
Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers…
KAT-Coder-V2 Technical Report
Fengxiang Li, Han Zhang, Haoyang Huang +43
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 in…
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
Jingxuan Xu, Ken Deng, Weihao Li +36
Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workf…
KAT-Coder Technical Report
Zizheng Zhan, Ken Deng, Jinghui Wang +37
Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development wor…
HiPO: Hybrid Policy Optimization for Dynamic Reasoning in LLMs
Ken Deng, Zizheng Zhan, Wen Xiang +25
Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inef…
SeamlessFlow: A Trainer Agent Isolation RL Framework Achieving Bubble-Free Pipelines via Tag Scheduling
Jinghui Wang, Shaojie Wang, Yinghan Cui +24
We introduce SeamlessFlow, a server based reinforcement learning (RL) framework that addresses two core challenges in industrial scale RL: (1) decoupling RL training from the compl…
KAT-V1: Kwai-AutoThink Technical Report
Zizheng Zhan, Ken Deng, Huaixi Tang +27
We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks, where an automatic thinkin…