Kimi-K3

Headlines · 3

1. 5d
   AREX-2 trains a 27B model with long-horizon reflection

   The AREX research group released AREX-2, a model based on Qwen3.8-27B and trained with long-horizon reflection data for machine-learning and algorithm-programming tasks. The team reported scores of 81.8 on MLE-bench Lite, 70.7 on Frontier-CS, 84.0 on BrowseComp and 52.6 on HLE. It also said the training helped capabilities transfer to deep research and scientific problem-solving. The report presents long-horizon reflection as a trainable and verifiable approach to recursive self-improvement, which is the team’s research interpretation rather than established proof of that capability.

   机器之心 · 🔥 0
2. 7d
   LLMs Show “Thinking Inertia” When Told to Answer Only

   Researchers from Tsinghua University, the University of Oxford and Stanford University tested six models from the Qwen3, DeepSeek, GPT and Gemini families across six benchmarks. They found that disabling thinking mode and asking for answers without reasoning reduced, but did not eliminate, visible calculations or derivations. Explicit reasoning was most common on open-ended questions, while yes-or-no questions prompted more direct answers. The study introduced three metrics to assess answer-only compliance, relevance of preceding text and explicit reasoning separately. The paper, code and trajectory data are public. The source reported that the paper was accepted at NeurIPS 2026, and a separate community member ran a small-scale independent test that also observed reasoning after thinking was disabled.

   新智元 · 🔥 0
3. Oct 14
   MLExpert: a 35B mixture-of-experts agentic model for autonomous ML engineering

   An arXiv paper submitted on 15 October proposes MLExpert, a 35B mixture-of-experts agentic model trained for autonomous long-horizon machine learning engineering (MLE) optimization. The authors built the Kaggle-MLE Factory to generate executable tasks and an interaction harness, used hierarchical agentic supervised fine-tuning to transfer tool-use and coding skills, and applied Windowed Interaction RL (WIRL), which rewards the multi-turn decisions between successive experiment results as a shared execution window. The authors report that on MLE-Bench Lite MLExpert raises the base model's average medal rate from 37.9% to 72.7%, comparable to larger frontier models such as Kimi-K3 and GLM-5.3, with further gains reported on NatureBench Lite, agent scaffold optimization and algorithm optimization.

   Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my Kimi-K3 experienceAsk about Kimi-K3