DSXiangLi/DecryptPrompt

★ 3,440⑂ 318

总结Prompt&LLM论文，开源数据&模型，AIGC应用

About DSXiangLi/DecryptPrompt

DSXiangLi/DecryptPrompt is an open-source project on GitHub, mainly written in several languages. 总结Prompt&LLM论文，开源数据&模型，AIGC应用 It currently holds 3,440 stars and 318 forks with 0 open issues, and was last pushed on an unknown date (repository created unknown).

Project Overview

AI Homed tracks it on the AI Prompt Engineering board.

GitHub Repository Details

Repository DSXiangLi/DecryptPrompt · default branch - · size 0 KB · watchers 0 · source: GitHub REST API and repository README

README

DecryptPrompt

如果LLM的突然到来让你感到沮丧，不妨读下主目录的Choose Your Weapon Survival Strategies for Depressed AI Academics

持续更新以下内容，Star to keep updated~

LLM资源汇总

跟着博客读论文

和AI一起搞事情

论文汇总

Harness

LoopArena
SKILL.state: Scalable Long-Horizon Agent Skills
A Programming Paradigm for Spatiotemporal Composability
AutoSaddler: Automatic Harness Optimization
Meta Harness
Loop Engineering: The Anthropic Playbook

Skill Evolution

WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
SkillOS: Learning Skill Curation for Self-Evolving Agents
Evolution Strategies for Skill Learning

图像生成

Neural Discrete Representation Learning
Denoising Diffusion Probabilistic Models
Scalable Diffusion Models with Transformers
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
High-Resolution Image Synthesis with Latent Diffusion Models

Post Train（和COT，RL有交集）

Inference Scaling
An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Are More LM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters :star:
Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning
Planning In Natural Language Improves LLM Search For Code Generation
ReST-MCTS∗ : LLM Self-Training via Process Reward Guided Tree Search
AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
Inference Scaling for Long-Context Retrieval Augmented Generation
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
InfAlign: Inference-aware language model alignment
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
What type of inference is planning?
Goedel-Prover: A Frontier Model for Open-Source Automated Theorem Proving
PROVABLE SCALING LAWS OF FEATURE EMERGENCE FROM LEARNING DYNAMICS OF GROKKING
Do Machine Learning Models Memorize or Generalize?
slow thinking COT
O1 Replication Journey: A Strategic Progress Report – Part 1 :star:
Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
Training Large Language Models to Reason in a Continuous Latent Space
Beyond A∗ : Better Planning with Transformers via Search Dynamics Bootstrapping
o1-Coder: an o1 Replication for Coding
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Sky-T1: Train your own O1 preview model within $450
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking :star:
Demystifying Long Chain-of-Thought Reasoning in LLMs
Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
Huggingface Open R1
CODEI/O: Condensing Reasoning Patterns via Code Input-Output Prediction
Training Language Models to Reason Efficiently
s1: Simple test-time scaling
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking
ALPHAONE: Reasoning Models Thinking Slow and Fast at Test Time
O3 Related
Competitive Programming with Large Reasoning Models
RL COT原理
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
Think Deep, Not Just Long:Measuring LLM Reasoning Effort via Deep-Thinking Tokens
R1 Reprodce
LogicRL: Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning
SimpleR1
Huggingface Open R1
DianJin-R1: Evaluating and Enhancing Financial Reasoning in Large Language Models
Think Only When You Need with Large Hybrid-Reasoning Models
Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties
Skywork Open Reasoner 1 Technical Report
Learning to Reason: Training LLMs with GPT-OSS or DeepSeek R1 Reasoning Traces
RL Agent
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning
ToolRL: Reward is All Tool Learning Needs
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
Improving Multi-Turn Tool Use with Reinforcement Learning
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Reinforcement Learning for Machine Learning Engineering Agents
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
rStar2-Agent: Agentic Reasoning Technical Report
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
IN-THE-FLOW AGENTIC SYSTEM OPTIMIZATION FOR EFFECTIVE PLANNING AND TOOL USE
UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning
PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold
DeepAnalyze: Agentic Large Language Models for Autonomous Data Science
Thinking with Programming Vision: Towards a Unified View for Thinking with Images
Scaling Agent Learning via Experience Synthesis
CaveAgent: Transforming LLMs into Stateful Runtime Operators
经验学习
Welcome to the Era of Experience
Agent Learning via Early Experience
其他训练方式
QWENLONG-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
REWARDBENCH 2: Advancing Reward Model Evaluation
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
EVOLUTION STRATEGIES AT SCALE: LLM FINETUNING BEYOND REINFORCEMENT LEARNING
Learning to Reason Across Parallel Samples for LLM Reasoning
PARAM∆ FOR DIRECT WEIGHT MIXING: POST-TRAIN LARGE LANGUAGE MODEL AT ZERO COST
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains
RL Overview
Reinforcement Learning: An Overview
Towards a Unified View of Large Language Model Post-Training
RL数据集
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

Context Engineer

Lost in Compaction
A Survey of Context Engineering for Large Language Models
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Scaling Long-Horizon LLM Agent via Context-Folding
Towards a Science of Scaling Agent Systems
Budget-Aware Tool-Use Enables Effective Agent Scaling
Context Engineering 2.0
End-to-End Test-Time Training for Long Context
Single-Agent LLMs Outperform Multi-Agent Systems on Multi-Hop Reasoning Under Equal Thinking Token Budgets
Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned
Meta-Harness End-to-End Optimization of Model Harnesses
The-Complete-Guide-to-Building-Skill-for-Claude

New Model Architecture

Nemotron-Labs-Diffusion: A Tri-Mode Language Model
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
Less is More: Recursive Reasoning with Tiny Networks
Continuous Thought Machines
TiDAR: Think in Diffusion, Talk in Autoregression
Nested Learning: The Illusion of Deep Learning Architectures

主流LLMS和预训练

Kimi K2
GLM-130B: AN OPEN BILINGUAL PRE-TRAINED MODEL
PaLM: Scaling Language Modeling with Pathways
PaLM 2 Technical Report
GPT-4 Technical Report
Backpack Language Models
LLaMA: Open and Efficient Foundation Language Models
Llama 2: Open Foundation and Fine-Tuned Chat Models
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
Mistral 7B
Ziya2: Data-centric Learning is All LLMs Need
MEGABLOCKS: EFFICIENT SPARSE TRAINING WITH MIXTURE-OF-EXPERTS
TUTEL: ADAPTIVE MIXTURE-OF-EXPERTS AT SCALE
Phi1- Textbooks Are All You Need :star:
Phi1.5- Textbooks Are All You Need II: phi-1.5 technical report
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Gemini: A Family of Highly Capable Multimodal Models
In-Context Pretraining: Language Modeling Beyond Document Boundaries
LLAMA PRO: Progressive LLaMA with Block Expansion
QWEN TECHNICAL REPORT
Fewer Truncations Improve Language Modeling
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
Phi-4 Technical Report
Byte Latent Transformer: Patches Scale Better Than Tokens
Qwen2.5 Technical Report
DeepSeek-V3 Technical Report
Mixtral of Experts
DeepSeek_R1 :star:
KIMI K1.5: SCALING REINFORCEMENT LEARNING WITH LLMS :star:
CWM: An Open-Weights LLM for Research on Code Generation with World Models
DeepSeek V3.2 Tech Report
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
思维链 (prompt_chain_of_thought)
基础&进阶用法
【zero-shot-COT】 Large Language Models are Zero-Shot Reasoners :star:
【few-shot COT】 Chain of Thought Prompting Elicits Reasoning in Large Language Models :star:
【SELF-CONSISTENCY 】IMPROVES CHAIN OF THOUGHT REASONING IN LANGUAGE MODELS
【LEAST-TO-MOST】 PROMPTING ENABLES COMPLEX REASONING IN LARGE LANGUAGE MODELS :star:
【TOT】Tree of Thoughts: Deliberate Problem Solving with Large Language Models :star:
【Plan-and-Solve】 Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
【Verify-and-Edit】: A Knowledge-Enhanced Chain-of-Thought Framework
【GOT】Beyond Chain-of-Thought, Effective Graph-of-Thought Reasoning in Large Language Models
【TOMT】Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
【LAMBADA】: Backward Chaining for Automated Reasoning in Natural Language
【AOT】Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models :star:
【GOT】Graph of Thoughts: Solving Elaborate Problems with Large Language Models :star:
【PHP】Progressive-Hint Prompting Improves Reasoning in Large Language Models
【HtT】LARGE LANGUAGE MODELS CAN LEARN RULES :star:
【DIVSE】DIVERSITY OF THOUGHT IMPROVES REASONING ABILITIES OF LARGE LANGUAGE MODELS
【CogTree】From Complex to Simple: Unraveling the Cognitive Tree for Reasoning with Small Language Models
【Step-Back】Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models :star:
【OPRO】LARGE LANGUAGE MODELS AS OPTIMIZERS :star:
【BOT】Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Abstraction-of-Thought Makes Language Models Better Reasoners
【SymbCoT】Faithful Logical Reasoning via Symbolic Chain-of-Thought
【XOT】EVERYTHING OF THOUGHTS : DEFYING THE LAW OF PENROSE TRIANGLE FOR THOUGHT GENERATION
【IoT】Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning
【DOT】On the Diagram of Thought
【ROT】Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up.
Thinking Forward and Backward: Effective Backward Planning with Large Language Models
【KR】K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning
【Self-Discover】SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
【Theory-of-Mind】HOW FAR ARE LARGE LANGUAGE MODELS FROMAGENTS WITH THEORY-OF-MIND?
【PC-SUBQ】Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation
Reverse Thinking Makes LLMs Stronger Reasoners
Chain of Draft: Thinking Faster by Writing Less
Atom of Thoughts for Markov LLM Test-Time Scaling
非传统COT问题分解方向
Decomposed Prompting A MODULAR APPROACH FOR Solving Complex Tasks
Successive Prompting for Decomposing Complex Questions
分领域COT [Math, Code, Tabular, QA]
Solving Quantitative Reasoning Problems with Language Models
SHOW YOUR WORK: SCRATCHPADS FOR INTERMEDIATE COMPUTATION WITH LANGUAGE MODELS
Solving math word problems with processand outcome-based feedback
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering
LEARNING PERFORMANCE-IMPROVING CODE EDITS
Chain of Code: Reasoning with a Language Model-Augmented Code Emulator
原理分析
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems :star:
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters :star:
TEXT AND PATTERNS: FOR EFFECTIVE CHAIN OF THOUGHT IT TAKES TWO TO TANGO
Towards Revealing the Mystery behind Chain of Thought: a Theoretical Perspective
Large Language Models Can Be Easily Distracted by Irrelevant Context
Chain-of-Thought Reasoning Without Prompting
Inductive or Deductive? Rethinking the Fundamental Reasoning Abilities of LLMs
Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning :star:
Why think step by step? Reasoning emerges from the locality of experience
Internal Consistency and Self-Feedback in Large Language Models: A Survey :star:
Iteration Head: A Mechanistic Study of Chain-of-Thought :star:
The Impact of Reasoning Step Length on Large Language Models :star:
Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
Do LLMs Really Think Step-by-step In Implicit Reasoning?
Cognitive Foundations for Reasoning and Their Manifestation in LLMs
小模型COT蒸馏
Specializing Smaller Language Models towards Multi-Step Reasoning :star:
Teaching Small Language Models to Reason
Large Language Models are Reasoning Teachers
Distilling Reasoning Capabilities into Smaller Language Models
The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning
Distilling System 2 into System 1
COT样本自动构建/选择
AutoCOT：AUTOMATIC CHAIN OF THOUGHT PROMPTING IN LARGE LANGUAGE MODELS
Active Prompting with Chain-of-Thought for Large Language Models
COMPLEXITY-BASED PROMPTING FOR MULTI-STEP REASONING
COT能力学习