Reasoning
29 items across the graph — tagged with Reasoning.
From the graph · 29
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
Democratizing Reinforcement Learning for LLMs
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Hugging Face model with 2918 likes. Tags: safetensors, qwen3_5, unsloth, qwen, qwen3.5, reasoning, chain-of-thought, Dense, image-text-to-text, conversational
[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
[EMNLP 2025] Awesome RAG Reasoning Resources
A `Neural = Symbolic` framework for sound and complete weighted real-value logic
Benchmark that evaluates LLMs using 759 NYT Connections puzzles extended with extra trick words
🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。
A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL wo…
A Model Context Protocol (MCP) server that provides advanced code analysis and reasoning capabilities powered by Google's Gemini AI
Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs
Unlock the hidden reasoning behind model answers.
Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks, PostgreSQL storage for multi-tenancy, and an eve…
Curated, opinionated index of post-R1 LLM × Reinforcement Learning. Many deep-dive blog posts cross-linked to many papers — GRPO, DAPO, DPO, PPO, RLHF, GSPO, CI…
Awesome Mixture of Experts (MoE): A Curated List of Mixture of Experts (MoE) and Mixture of Multimodal Experts (MoME)
FreeGPTHub: A truly free, unified GPT API gateway—unlike “fake-free” alternatives that hide paywalls behind quotas, trials, or mandatory top-ups. (真正免费的GPT统一接口，…
A framework for verifiable reasoning with language models.
ConDB: The KV-Cache Native Context Database
Efficient multi-token attribution for reasoning language models — Python package, CLI, and HTML token traces
Give your AI tools architecture-aware reasoning. Knowledge graph from any codebase — 14 LLM backends, impact analysis, confidence scores. Works with Claude Code…
Experiments with reasoning models, training techniques, papers
A no-string API framework for deploying schema-based reasoning into third-party apps
Testing Theory of Mind (ToM) in language models with epistemic logic
Open WebUI Logic Tree Multi-Model LLM Project - Advanced AI reasoning with Sakana AI's AB-MCTS and sophisticated multi-model collaboration
Open protocol for traversable knowledge networks. CBB traversal lets an 8B model match frontier AI on domain-specific queries.
A small reasoning model tuned to self-correct via failure traces.