6 papers
Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
Shengjie Wang, Guanghe Li, Zonghan Yang +1
Solving complex long-horizon tasks requires strong planning and reasoning capabilities. Although datasets with explicit chain-of-thought (CoT) rationales can substantially benefit…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
Kimi K2.5: Visual Agentic Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +339
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that…
Kimi-Dev: Agentless Training as Skill Prior for SWE-Agents
Zonghan Yang, Shengjie Wang, Kelin Fu +18
Large Language Models (LLMs) are increasingly applied to software engineering (SWE), with SWE-bench as a key benchmark. Solutions are split into SWE-Agent frameworks with multi-tur…
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages
Yongdong chi, Hanqing Wang, Zonghan Yang +4
Text-to-SQL transforms the user queries from natural language to executable SQL programs, enabling non-experts to interact with complex databases. Existing prompt-based methods cra…
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Kimi Team, Angang Du, Bofei Gao +93
Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learni…