reasoning-language-models

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Democratizing AI scientists with ToolUniverse

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

[EMNLP 2025] Awesome RAG Reasoning Resources

[ICLR 2026] VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning

A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.

Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".

Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.

[CVPR 2026 Highlight] ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering

Sudoku4LLM is a Sudoku dataset generator for training and evaluating reasoning in Large Language Models (LLMs). It offers customizable puzzles, difficulty levels, and 11 serialization formats to support structured data reasoning and Chain of Thought (CoT) experiments.