🚀 MassGen: An Open-Source Multi-Agent Scaling System for Collaborative AI with the Goal of Continuous Self-Improvement. Featuring parallel agent orchestration across frontier open and closed weight models, MCP integration, code execution, and intelligent consensus building for collective intelligence. Docs: docs.massgen.ai

Inference-time scaling for LLMs-as-a-judge.

[ICCV 2025] Video-T1: Test-Time Scaling for Video Generation

Official codebase for "Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling".

SE-Agent is a self-evolution framework for LLM Code agents. It enables trajectory-level evolution to exchange information across reasoning paths via Revision, Recombination, and Refinement, expanding the search space and escaping local optima. On SWE-bench Verified, it achieves SOTA performance

Repo of paper "Free Process Rewards without Process Labels"

🔥[ICML'25] Official repository for the paper "Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search"

Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning (NeurIPS2026-SEA)

"what, how, where, and how well? a survey on test-time scaling in large language models" repository

A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and post-inference stages.

ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning

m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning in Large Language Models

Awesome-Parallel-Reasoning: Unlocking the reasoning potential of LLMs. Papers, Code, Resources & Survey.

Efficient Test-Time Scaling for Small Vision-Language Models, official implementation of the paper, test-time scaling via test-time augmentation

The official PyTorch implementation for the Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence

[EMNLP 2025 Main] LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models

In which language do these models reason when solving problems presented in different languages? Our findings reveal that, despite multilingual training, LRMs tend to default to reasoning in high-resource languages (e.g., English) at test time

Revolutionary Self-Evolving Language Model - 100% self-contained AI trained on 40M Wikipedia articles

Official implementation of the paper "First Finish Search: Efficient Test-Time Scaling in Large Language Models"