chain-of-thought

[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.

🔥 Building composable LLM applications & workflow with Java.

Agent skill for analyzing and improving prompts using 31 frameworks across 7 intent categories. Works with Claude Code, Gemini CLI, Cursor, Copilot, and 30+ Agent Skills compatible tools.

[ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

Enhancing LLMs with LoRA

This framework works as a form of user/machine calibration, with a focus on user-context and user-intent, deconstructing your ideas logically from A to B to Z.

A Python toolkit for chain-of-thought prompting 🐍

We introduce new zero-shot prompting magic words that improves the reasoning ability of language models: panel discussion!

This GitHub repository contains the complete code for building Business-Ready Generative AI Systems (GenAISys) from scratch. It guides you through architecting and implementing advanced AI controllers, intelligent agents, and dynamic RAG frameworks. The projects demonstrate practical applications across various domains.

[ACL 2025 Industry Track, Oral] Sentiment Reasoning for Healthcare

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

Awesome deliberative prompting: How to ask LLMs to produce reliable reasoning and make reason-responsive decisions.

Best Prompt Engineering Tools for 2026 AI Workflow Optimization

Top 10 Claude Prompt Optimization Frameworks 2026

An ongoing, collaborative meta-analysis about Human-AI-Interactions. We aggregate data and knowledge to build a non-abrasive, user-friendly prompting framework tailored to LLM mechanics, ensuring reasoning stability and a friction-free prompting environment that is safe for the human psyche and wellbeing.

Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.

Build an Autonomous Web3 AI Trading Agent (BASE + Uniswap V4 example)

Research papers about Chain of Thought (CoT)

DeepSeek V4 特化思维链引导规范：we need to 句式，任意 agent 客户端可接入（纯提示词层）