Large Reasoning Models (LRMs) often struggle to balance deep thinking with efficient generation. Prior methods use monotonic scaling (e.g. "more steps = better results") but lack flexibility. Enter AlphaOne: Modulated Reasoning at Test Time AlphaOne introduces a universal
@jiqizhixin
-
Congratulations to Unitree Robotics
By
–
Congratulations https://
x.com/UnitreeRobotic
/UnitreeRobotics/status/1929535811860750481
… -
R3-RAG: Reinforcement Learning for LLM Reasoning and Retrieval
By
–
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
Paper: https://
arxiv.org/pdf/2505.23794
.pdf
…
Code: https://
github.com/Yuan-Li-FNLP/R
3-RAG
… -
R3-RAG: Teaching LLMs to Think and Retrieve Step by Step
By
–
R3-RAG: Teaching LLMs to Think and Retrieve Step by Step R3-RAG is a reinforcement learning-enhanced RAG framework that teaches the LLM how to reason and retrieve in tandem—not just pull documents, but think while doing it. The key ideas include Cold Start Pretraining and
-
MathArena: Evaluating LLMs on Math Competitions
By
–
MathArena: Evaluating LLMs on Uncontaminated Math Competitions
Paper: https://
arxiv.org/pdf/2505.23281
.pdf
…
Page: https://
matharena.ai
Code: https://
github.com/eth-sri/mathar
ena
… -
State-of-the-art LLMs performance on uncontaminated math competitions
By
–
How do state-of-the-art LLMs perform on uncontaminated math competitions? Researchers at ETH Zurich set out to answer this by building MathArena, a benchmark designed to evaluate SOTA models on clean, competition-style math problems. They then tested leading models on this
-
OpenAI o3/o4-mini Function Calling Guide Cookbook
By
–
A new cookbook from OpenAI!
o3/o4-mini Function Calling Guide Link: https://
cookbook.openai.com/examples/o-ser
ies/o3o4-mini_prompting_guide
…
GitHub: https://
github.com/openai/openai-
cookbook/blob/main/examples/o-series/o3o4-mini_prompting_guide.ipynb
… -
Darwin Godel Machine: Self-Improving Agents Evolution
By
–
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Paper: https://
arxiv.org/pdf/2505.22954
.pdf
…
Code: https://
github.com/jennyzzt/dgm -
Darwin Gödel Machine: Self-Improving AI Architecture Era
By
–
The Self-Improving AI Era Begins: Meet the Darwin Gödel Machine (DGM) Current AI systems, even the most powerful, rely on fixed, human-designed architectures. They can't autonomously evolve, limiting the pace and scope of innovation. While meta-learning automates small
-
Fast-dLLM: Training-free Acceleration of Diffusion Language Models
By
–
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Paper: https://
arxiv.org/pdf/2505.22618
.pdf
…
Code: https://
github.com/NVlabs/Fast-dL
LM
…
Project Page: https://
nvlabs.github.io/Fast-dLLM