http://semanlink.net/tag/reasoning_models Documents tagged with Reasoning models (Inference-time scaling) http://www.semanlink.net/doc/2025/08/the_hidden_drivers_of_hrm_s_per > The HRM model architecture itself (the centerpiece of the paper) is not an important factor. 2025-08-16T14:39:18Z http://www.semanlink.net/doc/2025/08/2506_21734_hierarchical_reaso > Inspired by the hierarchical and multi-timescale processing in the human brain... 2025-08-16T14:35:57Z http://www.semanlink.net/doc/2025/03/2501_19393_s1_simple_test_ti "Researchers created an open rival to OpenAI’s o1 ‘reasoning’ model for under $50" [techcrunch.com](https://techcrunch.com/2025/02/05/researchers-created-an-open-rival-to-openais-o1-reasoning-model-for-under-50/) 2025-03-03T09:04:57Z http://www.semanlink.net/doc/2025/02/diffuse_one_reasoning_reflectio 2025-02-24T14:08:53Z http://www.semanlink.net/doc/2025/02/cameron_r_wolfe_ph_d_sur_x_ > To me, these are pivotal questions to answer for current research on open reasoning models: > - Do the smaller / distilled models generalize well? > - Are we missing any gaps in performance? > - How do these findings relate to findings from traditional LLM research? 2025-02-24T13:55:04Z http://www.semanlink.net/doc/2025/02/openai_o1_hub_%7C_openai > a new series of AI models designed to spend more time thinking before they respond 2025-02-24T13:45:41Z http://www.semanlink.net/doc/2025/02/deepseek_r1_model_by_deepseek_a > DeepSeek-R1 is a first-generation **reasoning model trained using large-scale reinforcement learning** (RL) to solve complex reasoning tasks across domains such as math, code, and language. The model leverages RL to develop reasoning capabilities, which are further enhanced through supervised fine-tuning (SFT) to improve readability and coherence. 2025-02-24T13:34:19Z http://www.semanlink.net/doc/2025/02/diffuse_one > There is an emerging pattern of fine-tuning a small language model followed by reinforcement learning. > A reasoning model is a large language model that is trained to output both a chain of thought and a response. The chain of thought should be relatively long ( > 1,000 tokens) and the reasoning should improve its performance relative to a similar-sized non-reasoning models. This is sometimes called "test-time" or "inference-time" scaling because reasoning models emit more tokens per completion and gain some performance as a result. 2025-02-24T13:21:09Z